Connect Tech+Talent is hiring an AI / ML Engineering Tech Lead for an onsite, full-time opportunity in Chennai, Tamil Nadu, India.
The successful candidate will lead an engineering pod responsible for designing, developing, and deploying production-grade AI platforms and agentic LLM workflows. The role requires strong software engineering expertise, hands-on experience building production AI/ML and LLM applications, and the ability to translate complex architectures into reliable production systems.
Key Responsibilities:
- Lead an engineering pod building production AI platforms and applications.
- Architect and implement agentic LLM workflows using modern AI orchestration frameworks.
- Design and develop advanced Retrieval-Augmented Generation (RAG), GraphRAG, hybrid search, reranking, and knowledge graph solutions.
- Build retrieval systems using vector databases, graph databases, and related technologies.
- Implement enterprise-grade AI security, guardrails, prompt-injection protection, jailbreak prevention, and red-teaming practices.
- Establish LLM evaluation, observability, prompt versioning, and performance-monitoring processes.
- Optimize AI application performance, reliability, and operating costs.
- Develop and maintain production-ready Python services and APIs.
- Work with cloud infrastructure, containers, Kubernetes, and CI/CD pipelines.
- Provide technical leadership, mentor engineers, guide architecture decisions, and support agile engineering delivery.
Required Qualifications:
- 5+ years of software engineering experience.
- 3+ years of production experience with AI/ML, LLMs, or related AI applications.
- Strong Python programming skills.
- Experience with FastAPI, Pydantic, and Asyncio.
- Experience with LangGraph, LangChain, AutoGen, CrewAI, or LlamaIndex.
- Hands-on knowledge of RAG, GraphRAG, hybrid search, reranking, and vector retrieval.
- Familiarity with Neo4j, RDF, ontologies, and vector databases such as Pinecone, Qdrant, Milvus, or Weaviate.
- Understanding of AI security, prompt injection, jailbreak protection, guardrails, and red teaming.
- Experience with evaluation and observability tools or frameworks such as RAGAS and TruLens.
- Familiarity with LLMOps, prompt versioning, and AI evaluation workflows.
- Experience with Docker, Kubernetes, GitHub Actions, MLflow, or Weights & Biases.
- Experience deploying production workloads on AWS, Azure, or GCP.
- Strong technical leadership, architecture, mentoring, and collaboration skills.
Work Location: Chennai, Tamil Nadu, India.
Work Arrangement: Onsite.
Employment Type: Full-time.
Benefits will be discussed during interview.