AI / ML Engineering Tech Lead

Connect Tech+Talent; Chennai; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Connect Tech+Talent seeks a hands-on AI / LLM Engineering Tech Lead to drive the technical execution of enterprise AI platforms in Chennai. The role combines architectural leadership with real coding to build agentic AI workflows, knowledge graphs, and advanced RAG systems with robust AI security safeguards.

You will lead a pod, translate architecture into production-ready code, optimize performance, and mentor engineers while shaping the strategy for scalable, secure AI solutions across cloud

Qualifications

• 5+ years of software engineering experience with 3+ years in production AI/ML/LLM solutions.
• Strong Python, FastAPI, Pydantic, and Asyncio knowledge.
• Hands-on experience with LangGraph, LangChain, AutoGen, CrewAI, or LlamaIndex.
• Strong knowledge of RAG, GraphRAG, Hybrid Search, Re-ranking, and Vector Retrieval.
• Experience with Neo4j, RDF/Ontologies, and Vector DBs such as Pinecone, Qdrant, Milvus, or Weaviate.
• Experience implementing AI Security, Guardrails, Prompt Injection/Jailbreak Protection, and Red Teaming.
• Knowledge of RAGAS, TruLens, LLMOps, prompt versioning, evaluation, and observability.
• Hands-on experience with Docker, Kubernetes, GitHub Actions, MLflow/W&B.
• Production experience with AWS, Azure, or GCP.
• Strong technical leadership, mentoring, architecture, and agile pod leadership experience.

Responsibilities

• Lead an engineering pod building production-grade AI platforms.
• Architect and develop autonomous/agentic LLM workflows.
• Build advanced RAG and Knowledge Graph solutions.
• Implement AI security and enterprise guardrails.
• Drive LLM evaluation, performance, cost optimization, and observability.
• Translate architecture into production-ready code and engineering execution.

Skills

Python

FastAPI

Pydantic

Asyncio

LangGraph

LangChain

AutoGen

CrewAI

LlamaIndex

RAG

GraphRAG

Hybrid search

Vector retrieval

Neo4j

RDF/Ontologies

Vector DBs

AI Security

Guardrails

Prompt Injection

Jailbreak Protection

LLMOps

Prompt Versioning

Observability

Docker

Kubernetes

GitHub Actions

MLflow

AWS

Azure

GCP

Technical Leadership

Tools

Docker

Kubernetes

GitHub Actions

MLflow/W&B

Job description

We are looking for a hands-on AI / LLM Engineering Tech Lead to drive the technical execution of enterprise AI platforms. The ideal candidate will combine strong architectural expertise with hands-on coding experience to build Agentic AI workflows, Knowledge Graphs, advanced RAG systems, and AI security safeguards.

Key Requirements

• 5+ years of software engineering experience with 3+ years in production AI/ML/LLM solutions
• Strong Python, FastAPI, Pydantic, and Asyncio
• Hands-on experience with LangGraph, LangChain, AutoGen, CrewAI, or LlamaIndex
• Strong knowledge of RAG, GraphRAG, Hybrid Search, Re-ranking, and Vector Retrieval
• Experience with Neo4j, RDF/Ontologies, and Vector DBs such as Pinecone, Qdrant, Milvus, or Weaviate
• Experience implementing AI Security, Guardrails, Prompt Injection/Jailbreak Protection, and Red Teaming
• Knowledge of RAGAS, TruLens, LLMOps, prompt versioning, evaluation, and observability
• Hands-on experience with Docker, Kubernetes, GitHub Actions, MLflow/W&B
• Production experience with AWS, Azure, or GCP
• Strong technical leadership, mentoring, architecture, and agile pod leadership experience

What You'll Do

• Lead an engineering pod building production-grade AI platforms
• Architect and develop autonomous/agentic LLM workflows
• Build advanced RAG and Knowledge Graph solutions
• Implement AI security and enterprise guardrails
• Drive LLM evaluation, performance, cost optimization, and observability
• Translate architecture into production-ready code and engineering execution