Key responsibilities

• Design, build, and operate production grade AI services/APIs, owning reliability, scalability, and performance SLOs.
• Implement MLOps best practices (experiment tracking, model packaging, CI/CD for models, automated testing, feature and model registries, telemetry) to reduce time to production.
• Drive DevOps automation (infrastructure as code, containerization, orchestration) and secure delivery with least privilege, secrets management, and policy-as-code.
• Lead deployment of AI components to AWS/Azure (containers, serverless, managed ML platforms) with strong observability and rollback plans.
• Collaborate cross functionally to translate product and analytics requirements into well designed APIs, contracts, and SLAs.

Must have skills

• MLOps (e.g., MLflow/Kubeflow/SageMaker/Azure ML), CI/CD for ML, model registry, monitoring
• DevOps (Docker, Kubernetes, IaC—Terraform/Bicep, GitHub/GitLab Actions/Azure DevOps)
• Python (production code quality, testing, packaging)
• Deployment to AWS/Azure (EKS/AKS, ECS/Fargate, Lambda/Functions, API Gateway/App Gateway)
• API development (FastAPI/Flask, OpenAPI/Swagger, authN/Z, rate limiting, versioning)

Good to have

• GenAI/Agentic concepts, vector databases, prompt engineering fundamentals

Qualifications & experience

• B.Tech/M.Tech/MS in CS/EE or equivalent.
• 4+ years in AI Engineering