33 Rag Pipelines Jobs - Page 2

1. Conversational AI & Call Transcription Development Develop and fine-tune automatic speech recognition (ASR) models Implement language model fine-tuning for industry-specific language. Develop speaker diarization techniques to distinguish speakers in multi-speaker conversations. 2. NLP & Generative AI Applications Build summarization models to extract key insights from conversations. Implement Named Entity Recognition (NER) to identify key topics. Apply LLMs for conversation analytics and context-aware recommendations. Design custom RAG (Retrieval-Augmented Generation) pipelines to enrich call summaries with external knowledge. 3. Sentiment Analysis & Decision Support Develop sentiment and intent classification models. Create predictive models that suggest next-best actions based on call content, engagement levels, and historical data. 4. AI Deployment & Scalability Deploy AI models using tools like AWS, GCP, Azure AI, ensuring scalability and real-time processing. Optimize inference pipelines using ONNX, TensorRT, or Triton for cost-effective model serving. Implement MLOps workflows to continuously improve model performance with new call data. What you will bring to the Table: Technical Skills 8+ Years of overall experience, Strong expertise in Speech-to-Text (ASR), NLP, and Conversational AI. Hands-on expertise with tools like Whisper, DeepSpeech, Kaldi, AWS Transcribe, Google Speech-to-Text. Proficiency in Python, PyTorch, TensorFlow, Hugging Face Transformers. Experience with LLM fine-tuning, RAG-based architectures, and LangChain. Hands-on experience with Vector Databases (FAISS, Pinecone, Weaviate, ChromaDB) for knowledge retrieval. Experience deploying AI models using Docker, Kubernetes, FastAPI, Flask. Soft Skills Ability to translate AI insights into business impact. Strong problem-solving skills and ability to work in a fast-paced AI-first environment. Excellent communication skills to collaborate with cross-functional teams, including data scientists, engineers, and client stakeholders. Preferred Qualifications Experience in healthcare, pharma, or life sciences NLP use cases. Background in knowledge graphs, prompt engineering, and multimodal AI. Experience with Reinforcement Learning (RLHF) for improving conversation models.

Job Title: Executive AI Engineering Location: Andheri (Mumbai) Industry: Pharmaceutical Experience Required: 4+ years in Gen AI/ML, NLP application development About the Role: We are looking for a highly skilled Senior AI Engineer GenAI & Applied ML to independently design, develop, and deploy advanced AI solutions. This is a senior individual contributor role focused on building production-grade Generative AI systems, agentic applications, and intelligent bots using state-of-the-art LLMs, SLMs, and embedding models. You’ll work hands-on across the full AI stack — from fine-tuning models and writing APIs to implementing text-to-SQL and voice-enabled assistants. If you have a strong track record of single-handedly delivering complex AI systems and a deep understanding of modern ML and GenAI trends. Key Responsibilities: Design, build, and deploy production-ready AI solutions leveraging LLMs, SLMs, embedding models, and advanced ML techniques. Develop intelligent chat agents, voice-enabled bots, and autonomous agentic AI systems tailored to various domains and user contexts. Implement context-aware systems using RAG (Retrieval-Augmented Generation), custom embeddings, and vector databases to optimize relevance and response quality. Fine-tune and customize open-source and proprietary LLMs (e.g., GPT, Claude, LLaMA, Mistral, Phi 4) for domain-specific applications and enhanced performance. Build and expose scalable APIs to serve AI models and integrate them into broader application ecosystems. Own the full AI lifecycle — from architecture and experimentation to deployment and performance tuning. Translate business needs into technical blueprints in collaboration with product owners, data teams, and domain experts. Proactively research and prototype with the latest advancements in GenAI, agent frameworks, and multimodal models to drive innovation. Understanding of evaluation frameworks for GenAI systems, including prompt robustness, hallucination mitigation, and human-in-the-loop feedback loops. Requirements: 4 + years of hands-on experience in building and deploying AI/ML/NLP applications, including at least 2 years working with LLMs or GenAI systems in production environments. Proven experience with state-of-the-art LLMs/SLMs , such as GPT-3.5/4, Claude, LLaMA, Mistral, or similar, including prompt engineering, model evaluation, and fine-tuning. Practical expertise in building RAG pipelines , designing embedding workflows , and using vector databases like FAISS, Pinecone, or Weaviate. Strong Python programming skills with experience in Hugging Face Transformers , LangChain , LanGraph, OpenAI/Anthropic SDKs , and other GenAI frameworks. Solid grasp of ML/NLP fundamentals including data preprocessing , model optimization , evaluation metrics , and real-world deployment strategies . Familiarity with deploying AI models through APIs, cloud platforms, or containerized environments (e.g., Docker, FastAPI, Flask). Excellent analytical and debugging skills; ability to independently research, prototype, and solve complex problems end-to-end. Bonus: Exposure to voice AI systems , speech-to-text APIs, or audio-driven interfaces is an advantage. Nice to Have: Familiarity with regulatory and compliance frameworks relevant to AI in life sciences, such as GxP , HIPAA , GDPR , or similar standards. Experience integrating AI models into enterprise platforms , pharma-specific systems , or regulated IT environments . Knowledge of agent frameworks (e.g., AutoGen, CrewAI, LangGraph) and how to operationalize them in real-world use cases. Exposure to speech recognition APIs , voice interface design, or building voice-enabled assistants . Educational Qualifications: Bachelor’s Degree in Engineering (B.E./ B.Tech. ) or Master’s Degree in Computer Applications (MCA/ M.Tech) . Additional Qualifications in Artificial Intelligence, Machine Learning, or Data Science are highly desirable. Benefits We Offer: Access to a state-of-the-art facility equipped with modern and collaborative workspaces. Free gym facility to promote health and well-being of employees. Dynamic and inclusive work environment focused on innovation and continuous learning. Opportunity to work on impactful projects at the intersection of AI and life sciences. Competitive compensation.

Key Deliverables: Build and maintain scalable data pipelines for structured and unstructured data Implement ETL/ELT processes and integrate with GenAI systems Develop solutions using cloud platforms and big data technologies Collaborate with cross-functional teams to support data governance and AI initiatives Role Responsibilities: Design and develop high-performance data solutions for GenAI use cases Translate business needs into technical architecture and data workflows Ensure data quality, privacy, and security across systems Optimize data infrastructure and support continuous integration/deployment

* If you are 5+ years experienced and Immediate joiner , please apply: https://docs.google.com/forms/d/e/1FAIpQLScorR1zEgu9FvDHO-4gjJEOPhk_2tJE6cgftARiy9rwcVcDHg/viewform 5+ years of experience as a backend or full-stack engineer with a strong backend focus Advanced proficiency in Python Practical experience integrating LLMs (e.g., RAG pipelines, agent frameworks, LangChain, LangGraph, or similar) Background in machine learning engineering is a strong plus Solid understanding of service architecture and production deployment workflows Hands-on LLM integration in production (not academic/chatbot-only experience) Expertise in designing production-grade APIs and backend services Strong knowledge of async workflows, deployment, observability, and performance *This is a software engineering role (not data science, analytics, or annotation)* Description: A complete remote role, you can use your own laptop. 8hrs/day, Mon-Fri required Eligibility: Candidates with 5+ years of relevant professional experience are eligible to apply.Must possess strong communication skills , both written and verbal.Should have proven expertise in the specific field or role being applied for. Interview Pattern: Screening Interview - 30 min on google meet Second Interview - 60 min Final Client Interview - 30 min Govt Id should be shown in all interviews and camera is a must. Timings: 8 hrs/day, Mon-Fri Salary will be competitive above the market standards and will be calculated on hourly basis. Role & responsibilities Preferred candidate profile : Immediate Joiners

Greetings of the Day !! We have job opening for UiPath Developer with one of our clients . if you are interested for this position please share update resume . Location : Bangalore/ Pune/Hyderabad/ Indore Job Title: Tech Lead Intelligent Automation (UiPath + LLM Integration) Job Summary We are looking for a Tech Lead with deep expertise in UiPath as the primary automation platform and a strong background in integrating Large Language Models (LLMs) to enhance intelligent automation capabilities. This role involves leading solution design, architecture, and implementation of enterprise-grade automation systems that combine RPA with AI/LLM features such as document understanding, translation, and conversational automation. As a Tech Lead, you will mentor teams, define best practices, and drive innovation using UiPath and LLM technologies across the automation landscape. Key Responsibilities Lead architecture, design, and delivery of UiPath automation solutions integrated with LLMs to solve complex business challenges. Work closely with stakeholders to identify automation opportunities and define technical strategies using UiPath, AI Center, Document Understanding, and LLM APIs. Drive the integration of LLMs (e.g., OpenAI, Azure OpenAI, Google Gemini) into UiPath workflows for intelligent tasks such as summarization, classification, translation, and Q&A. Define reusable frameworks, standards, and best practices for LLM-augmented UiPath solutions. Guide development teams in building scalable and secure automation solutions using orchestrator, REFramework, and custom components. Own code reviews, solution documentation, and ensure delivery meets performance, security, and quality benchmarks. Provide technical leadership, mentorship, and training to UiPath developers and LLM engineers. Stay ahead of automation and AI trends, and proactively propose innovations aligned with business goals. Required Skills & Qualifications Bachelors or Masters degree in Computer Science, Engineering, or related discipline. 7+ years of experience in automation , with at least 5 years of hands-on UiPath experience including enterprise-grade solution delivery. Strong experience with UiPath Orchestrator, AI Center, Document Understanding , and REFramework. Hands-on experience in integrating LLMs into UiPath workflows using REST APIs, Python components, or custom activities. Deep understanding of prompt engineering, chunking, embeddings, and LLM-based document processing strategies. Proficiency in Python and API integration for external AI/LLM systems. Solid understanding of cloud AI services (Azure AI, Vertex AI, AWS AI) and vector databases (FAISS, Pinecone, Weaviate). Excellent communication, stakeholder management, and team leadership skills. Proven experience in mentoring teams, driving automation strategy, and ensuring solution scalability and maintainability. Preferred Skills (Nice to Have) UiPath Solution Architect or Advanced RPA Developer certification . Experience with LangChain , RAG pipelines, and LLM deployment at scale. Exposure to Power Platform, Microsoft Copilot Studio, or similar AI-enhanced low-code environments. Familiarity with DevOps practices in automation environments (CI/CD, version control, etc.). Knowledge of enterprise security, compliance, and governance in RPA + AI solutions. Thanks, Shaswati

Job Description: We are seeking a highly skilled and passionate AI/ML Engineer with strong expertise in Generative AI and Large Language Models (LLMs) . The ideal candidate will have hands-on experience in building, fine-tuning, and deploying agentic AI systems using modern GenAI frameworks. You will work on cutting-edge projects involving prompt engineering , RAG pipelines , and memory architectures such as vector databases. Responsibilities: Design and implement AI/ML solutions using modern LLM architectures and agentic AI concepts . Build and optimize intelligent agents using frameworks such as LangChain, AutoGen, CrewAI , or Semantic Kernel . Develop and fine-tune generative AI models with Transformers , HuggingFace , OpenAI API , etc. Implement and enhance Retrieval-Augmented Generation (RAG) pipelines and memory systems like vector databases (e.g., FAISS, Pinecone). Write high-performance Python code to support experimentation, model integration, and API interactions. Collaborate cross-functionally with product, design, and engineering teams in an agile development environment. Deploy AI solutions on cloud platforms (AWS, Azure, or GCP) with a focus on scalability and performance. Stay updated with the latest advancements in the AI/ML/GenAI space. Required Experience: 3 to 8 years of experience in AI/ML , with at least 1 year in Generative AI / LLM-based projects . Proven expertise in Python programming and related libraries for ML/GenAI. Hands-on experience with one or more GenAI frameworks (LangChain, AutoGen, etc.). Solid understanding of prompt engineering , RAG , vector DBs , and agent-based systems . Cloud deployment experience (AWS, Azure, or GCP) is a must. Strong analytical and problem-solving skills.

Develop and deploy ML pipelines using MLOps tools, build FastAPI-based APIs, support LLMOps and real-time inferencing, collaborate with DS/DevOps teams, ensure performance and CI/CD compliance in AI infrastructure projects. Required Candidate profile Experienced Python developer with 4–8 years in MLOps, FastAPI, and AI/ML system deployment. Exposure to LLMOps, GenAI models, containerized environments, and strong collaboration across ML lifecycle

We're looking for an experienced AI/ML Technical Lead to architect and drive the development of our intelligent conversation engine. Youll lead model selection, integration, training workflows (RAG/fine-tuning), and scalable deployment of natural language and voice AI components. This is a foundational hire for a technically ambitious platform. Role & responsibilities AI System Architecture: Design the architecture of the AI-powered agent including LLM-based conversation workflows, voice bots, and follow-up orchestration. Model Integration & Prompt Engineering: Leverage APIs from OpenAI, Anthropic, or deploy open models (e.g., LLaMA 3, Mistral). Implement effective prompt strategies and retrieval-augmented generation (RAG) pipelines for contextual responses. Data Pipelines & Knowledge Management: Build secure data pipelines to ingest, embed, and serve tenant-specific knowledge bases (FAQs, scripts, product docs) using vector databases (e.g., Pinecone, Weaviate). Voice & Text Interfaces: Implement and optimize multimodal agents (text + voice) using ASR (e.g., Whisper), TTS (e.g., Polly), and NLP for automated qualification and call handling. Conversational Flow Orchestration: Design dynamic, stateful conversations that can take actions (e.g., book meetings, update CRM records) using tools like LangChain, Temporal, or n8n. Platform Scalability: Ensure models and agent workflows scale across tenants with strong data isolation, caching, and secure API access. Lead a Cross-Functional Team: Collaborate with backend, frontend, and DevOps engineers to ship intelligent, production-ready features. Monitoring & Feedback Loops: Define and monitor conversation analytics (drop-offs, booking rates, escalation triggers), and create pipelines to improve AI quality continuously. Preferred candidate profile Qualifications Must-Haves: 5+ years of experience in ML/AI, with at least 2 years leading conversational AI or LLM projects. Strong background in NLP, dialog systems, or voice AI preferably with production experience. Experience with OpenAI, or open-source LLMs (e.g. LLaMA, Mistral, Falcon) and orchestration tools (LangChain, etc.). Proficiency with Python and ML frameworks (Hugging Face, PyTorch, TensorFlow). Experience deploying RAG pipelines, vector DBs (e.g. Pinecone, Weaviate), and managing LLM-agent logic. Familiarity with voice processing (ASR, TTS, IVR design). Solid understanding of API-based integration and microservices. Deep care for data privacy, multi-tenancy security, and ethical AI practices. Nice-to-Haves: Experience with CRM ecosystems (e.g. Salesforce, HubSpot) and how AI agents sync actions to CRMs. Knowledge of sales pipelines and marketing automation tools. Exposure to calendar integrations (Google Calendar API, Microsoft Graph). Knowledge of Twilio APIs (SMS, Voice, WhatsApp) and channel orchestration logic. Familiarity with Docker, Kubernetes, CI/CD, and scalable cloud infrastructure (AWS/GCP/Azure). What We Offer Founding team role with strong ownership and autonomy Opportunity to shape the future of AI-powered sales Flexible work environment Competitive salary Access to cutting-edge AI tools and training resources Post your resume and any relevant project links (GitHub, blog, portfolio) to career@sourcdeskglobal.com. Include a short note on your most interesting AI project or voicebot/conversational AI experience.