Sr MLOps & Agentic AI Engineer

We are seeking an experienced Senior MLOps & Agentic AI Engineer to design, build, deploy, and secure production machine learning and generative AI systems. In this role, you will work closely with Data Science, Backend Engineering, and Product teams—as well as directly with client stakeholders—to build reliable, scalable, and secure AI infrastructure.
A core focus of this position is building and maintaining secure MCP (Model Context Protocol) connectors and APIs on AWS, enabling LLM-driven query engines to interact safely with relational databases and enterprise data warehouses under strict access control and security boundaries.
Key Responsibilities
GenAI & Database Integration: Design, deploy, and manage secure MCP (Model Context Protocol) connectors, database bridges, and tool-calling pipelines that allow AI models to query enterprise database environments accurately.
Security & Access Control: Implement and enforce zero-trust security best practices, including least-privilege access, AWS IAM roles, secrets management (AWS Secrets Manager/Vault), row/column-level database security, and read-only query boundaries.
Guardrails & Governance: Build safety guardrails for AI interfaces, including prompt injection defenses, SQL execution sandboxing, rate-limiting, and sanitized data handling to prevent unauthorized data exposure.
Model Deployment & Infrastructure: Deploy, containerize, and scale ML models and LLM services in cloud environments using Docker and AWS container orchestrators (ECS/EKS or Lambda).
Pipelines & CI/CD: Automate CI/CD workflows for ML models, microservices, and data integration pipelines. Ensure robust versioning, reproducibility, and zero-downtime rollback strategies.
Monitoring & Observability: Set up comprehensive logging, metrics, and alerting using systems like CloudWatch, Prometheus, Grafana, or Elasticsearch to track query accuracy, latency, data drift, and system reliability.
Client Communication & Governance: Serve as a trusted technical voice with clients—communicating architectural choices, security postures, and access boundaries with transparency, accountability, and professional maturity.
Required Skills & Experience
Experience: 4+ years in MLOps, ML Engineering, or Backend/DevOps with hands-on experience deploying production ML models and GenAI/LLM applications.
Languages & Core Tech: Strong proficiency in Python, SQL, and REST/gRPC service architectures.
GenAI & Tool-Calling: Direct experience with Model Context Protocol (MCP), LLM tool-calling frameworks (LangChain, LlamaIndex, or native API function calling), and agentic workflows (n8n).
Database & Data Security: Solid understanding of database architecture (PostgreSQL, MySQL, Redshift, etc.), connection pooling, RBAC, query parsing/sanitization, and secure integration patterns.
Cloud Infrastructure (AWS): Deep hands-on experience across AWS services, including IAM, Secrets Manager, VPC, ECS/EKS, Lambda, S3, and CloudWatch.
Containerization & CI/CD: Expertise with Docker, Kubernetes/EKS, and CI/CD tools (GitHub Actions, GitLab CI, or Jenkins).
Observability: Proven experience setting up logging, metrics, and alerting pipelines for production applications.
Professional Standards: High sense of ownership, strong security-first mindset, and excellent client-facing communication skills.
Good to Have
Experience with managed AI services such as AWS Bedrock, SageMaker, or Vertex AI.
Exposure to vector databases (PGVector, Pinecone, Qdrant, Chroma).
Experience with data pipeline orchestration tools (Airflow, Prefect) and data lake technologies (S3, Glue, Athena/Spark).
Familiarity with enterprise compliance standards (SOC2, HIPAA, GDPR).
Graduation from a top-tier engineering or technology institution such as IITs, IISc, BITS Pilani, or equivalent is a plus.

Work arrangement
Yes