Role : AI/ML Senior Engineer

Experience Level : 5+ Years

Location : Chennai

Role Overview :

We are seeking a high-ownership, hands-on AI / LLM Senior Engineer to drive the technical execution of our core AI platforms. In this role, you will bridge deep architectural vision with direct code-level execution.

You will collaborate with an agile engineering pod building enterprise-grade Agentic Workflows, Knowledge Graphs, and AI Security Safeguards.

Key Responsibilities :

- Hands-On Agentic & Knowledge Systems Development : Architect and code multi-modal LLM workflows and autonomous agentic systems. Implement knowledge graphs, dynamic ontologies, and advanced vector retrieval strategies (Hybrid Search, GraphRAG, Re-ranking).

- AI Security & Guardrails : Deploy active safeguards against prompt injection, model jailbreaks, hallucination, and data leakage. Build automated pipelines for continuous model evaluation (e.g., RAGAS, TruLens), dynamic prompt versioning, and latency tracking.

- Cost & Throughput Optimization : Optimize token consumption, context window management, caching, and model inference costs across multi-cloud deployments.

- Observability & Execution : Monitor model drift and data distribution shifts. Collaborate with Product Managers and Solution Architects to resolve complex edge cases and mentor the team.

Required Qualifications :

- 5+ years of core software engineering experience, including 3+ years specifically architecting and delivering AI/ML or LLM-based products into production.

- Proven track record leading agile pods and conducting technical design reviews.

- Master's in Computer Science, Data Science, AI, or equivalent practical experience.

- Professional certifications in AWS/GCP/Oracle/Claude are mandatory.

Tech Stack :

- Languages : Python (FastAPI, PyDantic, Asyncio), TypeScript, Go, or Java.

- Agentic Frameworks : LangGraph, AutoGen, CrewAI, LangChain, LlamaIndex, PyTorch, Hugging Face.

- Vector Engines & Knowledge Graphs : Qdrant, Pinecone, Milvus, Weaviate, Neo4j, RDF/Ontologies.

- MLOps & Infra : Docker, Kubernetes, GitHub Actions, MLflow, Weights & Biases, serverless AI infrastructure on AWS/GCP/Azure.