8 Evaluation Metrics Jobs

As an AI Engineer specializing in Gen AI, NLP, and Python, you will be responsible for developing multiple product features utilizing Deep Learning, NLP, Graph analytics, Cognitive search, Image processing, Process Automation, LangGraph, and LangSmith. With 5 - 12 years of experience, you will leverage your expertise in Python and GenAI to scale the AI model capabilities effectively. Your role will involve working with Python Azure function, SQL DB, Cognitive search, Evaluation Metrics, RAGAS, and Advance RAG to enhance the functionalities and performance of AI models. You will collaborate with a team of professionals to design and implement innovative solutions that meet the requirements of the projects. This position is based in all LTIM Office Locations, offering you the opportunity to contribute to cutting-edge projects and make a significant impact in the field of Artificial Intelligence. If you are passionate about AI, have a strong background in Python, and possess a deep understanding of Gen AI and Deep Learning, we encourage you to apply and join our dynamic team.,

You will be joining a European-based MNC that is transitioning its operations to Bangalore in a Hybrid work mode. As part of the team, you will need to demonstrate expertise in Core Machine Learning & Deep Learning. This includes a solid grasp of Transformer architectures such as ViT, CLIP, and BERT, as well as experience with contrastive learning techniques like SimCLR, MoCo, and CLIP. Additionally, knowledge of temporal embeddings and sequence modeling for video, fine-tuning large pre-trained models, and a comprehensive understanding of Deep Learning concepts will be essential for this role. Your technical and engineering skills should include proficiency in Python and deep learning frameworks like PyTorch (preferred) or TensorFlow. Familiarity with StreetClip or similar multimodal models, experience with video data pipelines, and the ability to optimize model training and inference for performance and scalability will be key responsibilities. In terms of data and evaluation, you should have experience working with large-scale video datasets such as Kinetics, HowTo100M, etc. Knowledge of evaluation metrics for video understanding and retrieval tasks, familiarity with embedding spaces, similarity metrics, and retrieval systems will also be required. It would be beneficial to have experience with multimodal learning (vision + text), familiarity with distributed training and model deployment, as well as contributions to open-source projects or publications in relevant areas. Ideally, you should hold a degree in Computer Science, Machine Learning, or a related field (Masters or PhD preferred) and have at least 3 years of experience in deep learning or computer vision projects. If you meet these qualifications and skills, please share your profiles at hiring@khey-digit.com.,

As a Staff Data Scientist at Uber Eats, you will play a crucial role in enhancing the search experience for millions of users worldwide. Your deep statistical expertise will drive decision-making, improve product performance, and ensure that our evaluations and insights are based on methodological rigor. Your responsibilities will include conducting robust statistical analyses on complex datasets to identify product opportunities, shape roadmap priorities, and optimize user experiences in search. You will design and evaluate A/B tests and quasi-experiments, applying best practices in experimental methodology to ensure high-quality, unbiased insights. Building and maintaining statistical frameworks for defining and measuring ground truth will be a key aspect of your role, to identify reliable signals for evaluating search relevance, personalization, and user satisfaction. You will apply advanced sampling strategies to construct representative datasets for both offline and online evaluation pipelines, ensuring scalability and statistical power. Developing rigorous evaluation metrics that reflect real-world product performance and align closely with user and business goals will be essential. Additionally, you will lead initiatives to enhance causal inference practices across the team, applying methods like matching, regression discontinuity, and difference-in-differences where appropriate. Collaborating with product managers, engineers, and other scientists, you will translate open-ended product questions into structured analytical approaches. Providing mentorship and technical leadership to other scientists, you will promote a culture of statistical excellence and continuous learning within the team. To excel in this role, you should have an M.S. or Bachelor's degree in Statistics, Economics, Mathematics, Operations Research, Computer Science, or a related quantitative field. With 10+ years of industry experience in data science or applied analytics, ideally in consumer products, search, or recommendation systems, you should possess deep expertise in ground truth design and evaluation methodologies for complex user-facing systems. Your proven experience with statistical sampling techniques, offline evaluation pipelines, experimentation design, causal inference, and observational data analysis will be valuable. Proficiency in tools like SQL, Python, and R for data manipulation, modeling, and visualization is required. Excellent communication skills are essential, as you will need to present statistical findings clearly and influence product and engineering decisions through data. Having a strong product sense and the ability to balance analytical rigor with practical business impact will be advantageous in this role.,

As a Deep Learning Engineer Intern, you will have the opportunity to work on our core ML stack, focusing on areas such as Computer Vision, Recommendation Systems, and LLM-based Features (optional). Working closely with our senior engineers, you will gain hands-on experience with real data, address edge-case challenges, and rapidly iterate on prototypes that drive our food-robotic machine. You will be an integral part of a focused 2-person full-time ML team, serving as our first intern and reporting directly to the Lead. This small team size ensures significant mentorship opportunities and allows you to make a direct impact on product development. Your responsibilities will include: - Working on tasks such as Ingredient Segmentation, Recipe Similarity, and Vision-Language Models - Packaging and deploying models for on-device inference and AWS services - Supporting data collection and annotation, refining datasets based on model performance - Iterating on experiments, tuning hyperparameters, testing augmentations, and documenting results We are looking for candidates with: - Strong fundamentals in Deep Learning (Transformers, CNNs) and classical ML (Logistic / Linear regression) - Hands-on experience with PyTorch in academic projects, internships, or personal work - Proficiency in Python and the broader ML ecosystem (NumPy, pandas) - Solid understanding of training pipelines, evaluation metrics, and experimental rigor - Eagerness to learn new domains such as NLP and recommendations Nice to have skills include prior exposure to LLMs or multimodal models, experience with computer vision in challenging real-world environments, and projects involving noisy, real-world datasets or edge-case-heavy scenarios. Working with us, you will enjoy: - Early ownership of ML features, contributing end-to-end to projects - Hands-on experience with real robotic systems in homes, witnessing your models in action - Direct access to senior ML engineers for mentorship in a small, focused team environment - Rapid feedback loops that allow you to prototype, deploy, and learn quickly - A clear growth path with strong potential for full-time conversion into our rapidly expanding ML team We are looking for candidates who are currently enrolled in a B.Tech or M.Tech program (3-4 years into their degree), possess strong math and ML fundamentals beyond using off-the-shelf libraries, thrive in an ambiguous, fast-paced startup environment, and are always curious, enjoying building, experimenting, and sharing insights. Location: Bangalore (4 days WFO & 1 day WFH) Duration: 3-6 month internship Compensation: 1,00,000/month To apply, ensure your resume includes a project portfolio with the following: - GitHub profile showcasing ML/deep learning projects - Public codebase from coursework, internships, or personal work - Kaggle notebooks or competition solutions with leaderboard standings,

Job Summary: We are seeking a highly motivated and skilled Project Manager to lead and manage AI-driven projects from conception to deployment. The ideal candidate will bridge the gap between business, data science, and engineering teams, ensuring smooth project execution, alignment with business objectives, and timely delivery. This role requires a deep understanding of machine learning (ML) concepts and AI technologies, coupled with strong project management experience. Key Responsibilities: Project Planning & Execution: Lead the planning, execution, and delivery of machine learning and AI projects from ideation through production. Define project scope, goals, deliverables and timelines in collaboration with stakeholders. Establish clear project roadmaps, milestones, and resource allocation plans. Stakeholder Management: Serve as the primary liaison between cross-functional teams, including data scientists, ML engineers, product managers and business stakeholders. Translate complex AI/ML concepts into business-friendly language for non-technical stakeholders. Manage expectations and ensure alignment between technical capabilities and business objectives. Team Leadership & Collaboration: Coordinate cross-functional teams to drive project success, ensuring collaboration between engineers, data scientists, analysts and business teams. Ensure that team members have clear objectives and are working efficiently toward the project's success. Risk Management & Problem Solving: Identify project risks and develop mitigation strategies. Solve project bottlenecks, troubleshoot technical challenges, and ensure continuous progress. Quality Control & Compliance: Ensure quality control throughout the ML/AI project lifecycle, including model performance and validation. Ensure adherence to ethical AI practices and compliance with data privacy regulations. Reporting & Documentation: Track project progress, provide regular status reports to stakeholders and present key findings. Maintain detailed project documentation, including timelines, deliverables, and performance metrics. Qualifications: Education & Experience: Bachelors degree in Computer Science, Data Science, Engineering, or a related field. A Masters degree or higher is a plus. 3+ years of experience in project management, with at least 1-3 years of experience in AI/ML-related projects. Technical Skills: Familiarity with machine learning frameworks (e.g., TensorFlow, PyTorch), data science tools (e.g., Jupyter, R, Python), and cloud platforms (AWS, Google Cloud, Azure). Understanding of AI/ML workflows, from data collection and preprocessing to model training, deployment, and monitoring. Basic understanding of algorithms, statistical models, data pipelines, and evaluation metrics. Project Management Skills: Proven track record of managing AI or software development projects through agile or traditional project management methodologies. Strong knowledge of project management tools (e.g., Jira, Asana, Trello) and version control systems (e.g., Git). Soft Skills: Excellent communication and interpersonal skills, with the ability to lead and inspire cross-functional teams. Strong problem-solving skills and an ability to navigate through ambiguity and technical complexity. High level of organization and attention to detail.,

Role - Lead AI Engineer Experience: 3+ years in AI/ML Location: Gurgaon, work from office About Tap Health: Tap Health is a deep-tech platform that is transforming chronic care management with AI and changing how you access health information. Powered by our proprietary Medical AI model, VaiD, Tap Health is designed to make healthcare accessible to millions. We are developing next-generation Digital Therapeutic products that redefine chronic illness management through AI-driven, hyper-personalized care. Our platform helps users manage conditions such as diabetes, hypertension, PCOS, pregnancy and asthma by delivering daily structured digital therapeutics, lifestyle interventions, personalized nutrition and exercise guidance and real-time monitoring, all without requiring human intervention. Leveraging AI and adaptive algorithms, Tap Health dynamically personalizes each users care journey, delivering enhanced insights, interventions, motivation, adherence and clinical outcomes at a fraction of traditional healthcare costs. Beyond Digital Therapeutics, the Tap Health platform also provides free primary illness diagnosis based on symptoms and instant health advice through a seamless, voice-first experience. www.tap.health Role Overview: Lead AI Engineer We are hiring a full-time Lead AI Engineer in Gurgaon to drive AI-driven healthcare innovations. The ideal candidate has 3+ years of AI/ML experience, 6+ months of GenAI production experience, and 1+ year of hands-on GenAI product development. You need to have a strong data science background and have expertise in GenAI, Agentic AI deployments, causal inference, and Bayesian modeling, with a strong foundation in LLMs and traditional models. You will be collaborating with the AI, Engineering, and Product teams to build scalable, consumer-focused healthcare solutions. As a Lead AI Engineer, you will be the go-to expertthe engineer others turn to when they hit roadblocks. You will mentor, collaborate, and enable high product velocity while fostering a culture of continuous learning and innovation. Skills & Experience The ideal candidate should have the following qualities: Strong understanding of fine-tuning, optimization, and neural architectures. Hands-on experience with Python, PyTorch, and FastAI frameworks. Experience running production workloads on one or more hyperscalers (AWS, GCP, Azure, Oracle, DigitalOcean, etc.). In-depth knowledge of LLMshow they work and their limitations. Ability to assess the advantages of fine-tuning, including dataset selection strategies. Understanding of Agentic AI frameworks, MCPs (Multi-Component Prompting), ACP (Adaptive Control Policies), and autonomous workflows. Familiarity with evaluation metrics for fine-tuned models and industry-specific public benchmarking standards in the healthcare domain. Knowledge of advanced statistical models, reinforcement learning, and Bayesian inference methods. Experience in Causal Inference and Experimentation Science to improve product and marketing outcomes. Proficiency in querying and analyzing diverse datasets from multiple sources to build custom ML and optimization models. Comfortable with code reviews and standard coding practices using Python, Git, Cursor, and CodeRabbit.,

Role & responsibilities We are seeking an experienced and technically strong Machine Learning Engineer to design, implement, and operationalize ML models across Google Cloud Platform (GCP) and Microsoft Azure. The ideal candidate will have a robust foundation in machine learning algorithms, MLOps practices, and experience deploying models into scalable cloud environments. Responsibilities: Design, develop, and deploy machine learning solutions for use cases in prediction, classification, recommendation, NLP, and time series forecasting. Translate data science prototypes into production-grade, scalable models and pipelines. Implement and manage end-to-end ML pipelines using: Azure ML (Designer, SDK, Pipelines), Data Factory, and Azure Databricks Vertex AI (Pipelines, Workbench), BigQuery ML, and Dataflow Build and maintain robust MLOps workflows for versioning, retraining, monitoring, and CI/CD using tools like MLflow, Azure DevOps, and GCP Cloud Build. Optimize model performance and inference using techniques like hyperparameter tuning, feature selection, model ensembling, and model distillation. Use and maintain model registries, feature stores, and ensure reproducibility and governance. Collaborate with cloud architects, and software engineers to deliver ML-based solutions. Maintain and monitor model performance in production using Azure Monitor, Prometheus, Vertex AI Model Monitoring, etc. Document ML workflows, APIs, and system design for reusability and scalability. Primary Skills required (Must Have Expereince): 5 -7 years of experience in machine learning engineering or applied ML roles. Advanced proficiency in Python, with strong knowledge of libraries such as Scikit-learn, Pandas, NumPy, XGBoost, LightGBM, TensorFlow, PyTorch. Solid understanding of core ML concepts: supervised/unsupervised learning, cross-validation, bias-variance tradeoff, evaluation metrics (ROC-AUC, F1, MSE, etc.). Hands-on experience deploying ML models using: Azure ML (Endpoints, SDK), AKS, ACI Vertex AI (Endpoints, Workbench), Cloud Run, GKE Familiarity with cloud-native tools for storage, compute, and orchestration: Azure Blob Storage, ADLS Gen2, Azure Functions GCP Storage, BigQuery, Cloud Functions Experience with containerization and orchestration (Docker, Kubernetes, Helm). Strong understanding of CI/CD for ML, model testing, reproducibility, and rollback strategies. Experience implementing drift detection, model explainability (SHAP, LIME), and responsible AI practices.

Designation: AI/ML Engineer Experience : 2 - 5 years exp Education : Bachelor's or Master's in Computer Science, AI/ML, Data Science, or related fields Job Location: Navi Mumbai (Onsite) Role. Key Responsibilities: Design and develop AI/ML models for OCR, focusing on handwritten, printed, and multi-language documents. Train and fine-tune custom OCR models using frameworks like TensorFlow, PyTorch, or Google Vertex AI, etc. Integrate OCR solutions into a browser-based platform using Node.js (backend) and React.js (frontend). Preprocess and analyze scanned or photographed documents to improve text recognition accuracy using tools like OpenCV. Evaluate and compare third-party OCR services (e.g., Google Vision, Azure OCR, Amazon Textract). Build intelligent data pipelines for document parsing, classification, and information extraction. Collaborate with full-stack developers to deploy AI models into production web apps. Keep up to date with advancements in AI tools, OCR technologies, and web integration strategies. Experience in diagram or symbol detection Required Skills & Qualifications:* Bachelor's or Master's in Computer Science, AI/ML, Data Science, or related fields 3+ years of proven experience with OCR technologies and document image processing Strong proficiency in Python for model development, training, and data pipelines Working knowledge of JavaScript, Node.js, and React.js for full-stack AI integration Hands-on experience with deep learning frameworks (TensorFlow, PyTorch, or similar) Demonstrated ability to preprocess and enhance document images using OpenCV or similar tools. Experience deploying ML models to production environments. Familiarity with version control (Git), containerization (Docker), and cloud services (AWS/GCP/Azure) *Good to Have Skills:* Experience with Agentic AI frameworks (LangChain, AutoGPT, or similar) Knowledge of RAG (Retrieval-Augmented Generation) architectures for document context Familiarity with LLM integration for enhanced document understanding Experience with multi-language document processing and non-Latin character recognition Understanding of diagram, table, and technical symbol detection in documents Background in MLOps tools (MLflow, DVC, Vertex AI) for model lifecycle management Experience developing autonomous AI agents for document processing automation Familiarity with prompt engineering for specialized OCR applications Interested candidate can apply there resume on email id :- hr@techplusinfotech.com .