5 Bentoml Jobs

Location: Mumbai, India Experience Level: 9 Plus Years Minimum Qualification: Masters Degree in Computer Science, Engineering, or related field. About the Role: Were looking for a strategic Senior MLOps Engineer to lead the end-to-end design, implementation, and scaling of our AI infrastructure. Youll partner with researchers, product teams, and DevOps to turn prototypes into production services that meet strict SLAs for latency, reliability, and cost efficiency. Responsibilities: Core MLOps Pipelines: Design and implement scalable ML pipelines (training, evaluation, deployment) for LLMs, CV, and multimodal models . Model Serving & CI/CD: Lead efforts in model serving, versioning, automated CI/CD, and real-time monitoring of AI workflows . Inference-as-a-Service: Build and optimize GPU-backed serving infrastructure targeting p99 latency < 100 ms, 99.9% uptime, and > 80% GPU utilization . Governance & Drift Detection: Drive initiatives on model governance, automated drift detection (?10% false positives), and data-management best practices . Vector Search & Agent Orchestration: Integrate vector databases (Qdrant, Pinecone) for low-latency semantic retrieval, and build agentic workflows using LangChain or similar frameworks. Enterprise Multi-Tenancy: Architect RBAC-driven, isolated ML services to securely serve 100500+ organizations. Observability & Logging: Design Prometheus/Grafana dashboards, ELK/Fluentd logging pipelines, and alerting for all ML workloads. CI/CD for Inference APIs: Maintain CI/CD pipelines for Python (FastAPI) and TypeScript (NestJS) inference services. Metrics & Cost Optimization: Define and track SLAs/SLOs, optimize cloud spend by ? 20% year-over-year, and ensure GPU clusters operate at > 80% utilization. Cross-Functional Leadership: Partner with AI researchers, product managers, and legal to align MLOps standards with compliance and roadmap goals. Mentorship & Community: Mentor junior engineers, run quarterly brown-bags, own onboarding docs (upskill 5+ engineers/quarter), and publish ? 1 open-source contribution or talk annually. Requirements : 914 years in software engineering, including ? 4 years in MLOps or ML infrastructure Strong expertise in cloud platforms (AWS/GCP/Azure), Kubernetes, Docker, Terraform, Helm, Kubeflow, and MLflow Experience with inference frameworks (Triton, TensorFlow Serving, BentoML, TorchServe) Familiarity with distributed training, workload schedulers, and GPU-cluster orchestration Proficiency in Python, TypeScript, and infrastructure-as-code (Terraform, Helm, etc.) Proven track record building reliable, scalable ML systems in production. Plus These Critical Skills: Vector DB integration (Qdrant, Pinecone) Agent orchestration (LangChain, LlamaIndex) Multi-tenant security and RBAC Observability stacks (Prometheus/Grafana, ELK) CI/CD for FastAPI/NestJS services Preferred : Masters/PhD in CS/AI and certifications such as AWS ML Specialty, Google Cloud Professional ML Engineer, or CNCF CKA/CKAD. Prior experience at AI-focused startups or enterprises scaling ML for 100500 orgs. Understanding of low-latency streaming inference or agent-based LLM systems. Excellent written and verbal communication, and a proven ability to drive consensus across functions. Show more Show less

As a Senior Machine Learning Engineer with over 10 years of experience, you will play a crucial role in designing, building, and deploying scalable machine learning systems in production. In this role, you will collaborate closely with data scientists to operationalize models, take ownership of ML pipelines from end to end, and enhance the reliability, automation, and performance of our ML infrastructure. Your primary responsibilities will include designing and constructing robust ML pipelines and services for training, validation, and model deployment. You will work in collaboration with various stakeholders such as data scientists, solution architects, and DevOps engineers to ensure alignment with project goals and requirements. Additionally, you will be responsible for ensuring cloud integration compatibility with AWS and Azure, building reusable infrastructure components following best practices in DevOps and MLOps, and adhering to security standards and regulatory compliance. To excel in this role, you should possess strong programming skills in Python, have deep experience with ML frameworks such as TensorFlow, PyTorch, and Scikit-learn, and be proficient in MLOps tools like MLflow, Airflow, TFX, Kubeflow, or BentoML. Experience in deploying models using Docker and Kubernetes, familiarity with cloud platforms and ML services, and proficiency in data engineering tools are essential for success in this position. Additionally, knowledge of CI/CD, version control, and infrastructure as code along with experience in monitoring/logging tools will be advantageous. Good-to-have skills include experience with feature stores and experiment tracking platforms, knowledge of edge/embedded ML, model quantization, and optimization, as well as familiarity with model governance, security, and compliance in ML systems. Exposure to on-device ML or streaming ML use cases and experience in leading cross-functional initiatives or mentoring junior engineers will also be beneficial. Joining Ericsson will provide you with an exceptional opportunity to leverage your skills and creativity to address some of the world's toughest challenges. You will be part of a diverse team of innovators who are committed to pushing the boundaries of innovation and crafting groundbreaking solutions. As a member of this team, you will be challenged to think beyond conventional limits and contribute to shaping the future of technology.,

About the Role We are looking for an experienced DevOps Engineer to join our engineering team. This role involves setting up, managing, and scaling development, staging, and production environments both on AWS cloud and on-premise (open source stack) . You will be responsible for CI/CD pipelines, infrastructure automation, monitoring, container orchestration, and model deployment workflows for our enterprise applications and AI platform. Key Responsibilities Infrastructure Setup & Management Design and implement cloud-native architectures on AWS and be able to manage on-premise open source environments when required . Automate infrastructure provisioning using tools like Terraform or CloudFormation. Maintain scalable environments for dev, staging, and production . CI/CD & Release Management Build and maintain CI/CD pipelines for backend, frontend, and AI workloads. Enable automated testing, security scanning, and artifact deployments. Manage configuration and secret management across environments. Containerization & Orchestration Manage Docker-based containerization and Kubernetes clusters (EKS, self-managed K8s) . Implement service mesh, auto-scaling, and rolling updates. Monitoring, Security, and Reliability Implement observability (logging, metrics, tracing) using open source or cloud tools. Ensure security best practices across infrastructure, pipelines, and deployed services. Troubleshoot incidents, manage disaster recovery, and support high availability. Model DevOps / MLOps Set up pipelines for AI/ML model deployment and monitoring (LLMOps). Support data pipelines, vector databases, and model hosting for AI applications. Required Skills and Qualifications Cloud & Infra Strong expertise in AWS services : EC2, ECS/EKS, S3, IAM, RDS, Lambda, API Gateway, etc. Ability to set up and manage on-premise or hybrid environments using open source tools. DevOps & Automation Hands-on experience with Terraform / CloudFormation . Strong skills in CI/CD tools such as GitHub Actions, Jenkins, GitLab CI/CD, or ArgoCD. Containerization & Orchestration Expertise with Docker and Kubernetes (EKS or self-hosted). Familiarity with Helm charts, service mesh (Istio/Linkerd). Monitoring / Observability Tools Experience with Prometheus, Grafana, ELK/EFK stack, CloudWatch . Knowledge of distributed tracing tools like Jaeger or OpenTelemetry. Security & Compliance Understanding of cloud security best practices . Familiarity with tools like Vault, AWS Secrets Manager. Model DevOps / MLOps Tools (Preferred) Experience with MLflow, Kubeflow, BentoML, Weights & Biases (W&B) . Exposure to vector databases (pgvector, Pinecone) and AI pipeline automation . Preferred Qualifications Knowledge of cost optimization for cloud and hybrid infrastructures . Exposure to infrastructure as code (IaC) best practices and GitOps workflows. Familiarity with serverless and event-driven architectures . Education Bachelors degree in Computer Science, Engineering, or related field (or equivalent experience). What We Offer Opportunity to work on modern cloud-native systems and AI-powered platforms . Exposure to hybrid environments (AWS and open source on-prem). Competitive salary, benefits, and growth-oriented culture. Show more Show less

The Senior Data Science Lead is a pivotal role responsible for driving the research, development, and deployment of semi-autonomous AI agents to solve complex enterprise challenges. This role involves hands-on experience with LangGraph, leading initiatives to build multi-agent AI systems that operate with greater autonomy, adaptability, and decision-making capabilities. The ideal candidate will have deep expertise in LLM orchestration, knowledge graphs, reinforcement learning (RLHF/RLAIF), and real-world AI applications. As a leader in this space, they will be responsible for designing, scaling, and optimizing agentic AI workflows, ensuring alignment with business objectives while pushing the boundaries of next-gen AI automation. Key Responsibilities: 1. Architecting & Scaling Agentic AI Solutions: - Design and develop multi-agent AI systems using LangGraph for workflow automation, complex decision-making, and autonomous problem-solving. - Build memory-augmented, context-aware AI agents capable of planning, reasoning, and executing tasks across multiple domains. - Define and implement scalable architectures for LLM-powered agents that seamlessly integrate with enterprise applications. 2. Hands-On Development & Optimization: - Develop and optimize agent orchestration workflows using LangGraph, ensuring high performance, modularity, and scalability. - Implement knowledge graphs, vector databases (Pinecone, Weaviate, FAISS), and retrieval-augmented generation (RAG) techniques for enhanced agent reasoning. - Apply reinforcement learning (RLHF/RLAIF) methodologies to fine-tune AI agents for improved decision-making. 3. Driving AI Innovation & Research: - Lead cutting-edge AI research in Agentic AI, LangGraph, LLM Orchestration, and Self-improving AI Agents. - Stay ahead of advancements in multi-agent systems, AI planning, and goal-directed behavior, applying best practices to enterprise AI solutions. - Prototype and experiment with self-learning AI agents, enabling autonomous adaptation based on real-time feedback loops. 4. AI Strategy & Business Impact: - Translate Agentic AI capabilities into enterprise solutions, driving automation, operational efficiency, and cost savings. - Lead Agentic AI proof-of-concept (PoC) projects that demonstrate tangible business impact and scale successful prototypes into production. 5. Mentorship & Capability Building: - Lead and mentor a team of AI Engineers and Data Scientists, fostering deep technical expertise in LangGraph and multi-agent architectures. - Establish best practices for model evaluation, responsible AI, and real-world deployment of autonomous AI agents.,

As a Machine Learning Engineer, you will be responsible for designing and implementing scalable machine learning models throughout the entire lifecycle - from data preprocessing to deployment. Your role will involve leading feature engineering and model optimization efforts to enhance performance and accuracy. Additionally, you will build and manage end-to-end ML pipelines using MLOps practices, ensuring seamless deployment, monitoring, and maintenance of models in production environments. Collaboration with data scientists and product teams will be key in understanding business requirements and translating them into effective ML solutions. You will conduct advanced data analysis, create visualization dashboards for insights, and maintain detailed documentation of models, experiments, and workflows. Moreover, mentoring junior team members on best practices and technical skills will be part of your responsibilities to foster growth within the team. In terms of required skills, you must have at least 3 years of experience in machine learning development, with a focus on the end-to-end model lifecycle. Proficiency in Python using Pandas, NumPy, and Scikit-learn for advanced data handling and feature engineering is crucial. Strong hands-on expertise in TensorFlow or PyTorch for deep learning model development is also a must-have. Desirable skills include experience with MLOps tools like MLflow or Kubeflow for model management and deployment, familiarity with big data frameworks such as Spark or Dask, and exposure to cloud ML services like AWS SageMaker or GCP AI Platform. Additionally, working knowledge of Weights & Biases and DVC for experiment tracking and versioning, as well as experience with Ray or BentoML for distributed training and model serving, will be considered advantageous. Join our team and contribute to cutting-edge machine learning projects while continuously improving your skills and expertise in a collaborative and innovative environment.,