Gen Ai Lead

Tata Consultancy Services; Irving (TX); On-site; USD 80,000 - 125,000; Full time

Job summary

Tata Consultancy Services Limited in Irving, TX is seeking a GenAI Engineer to own end-to-end delivery of AI applications, from design and testing to cloud deployment and monitoring.

The role emphasizes building autonomous agents, grounding AI with advanced retrieval systems, and optimizing performance while upholding governance and safety standards. Mentorship and cross-team collaboration are core expectations.

Qualifications

• Expert Python development experience.
• Hands-on experience with LangChain, LlamaIndex, or similar frameworks.
• Experience with vector databases and knowledge graphs.

Responsibilities

• Own the full lifecycle of GenAI apps from design to cloud deployment and monitoring.
• Build autonomous agents that reason and execute multi-step workflows using tools and APIs.
• Implement RAG & Graph RAG to ground AI in enterprise data and reduce hallucinations.
• Tune latency, throughput, and cost for large-scale LLM inference.
• Establish governance and safety practices for responsible AI.
• Mentor junior engineers and bridge technical and business teams.

Skills

Python

Go

Java

C++

LangChain

LlamaIndex

LangGraph

CrewAI

AutoGen

Vector DB

Neo4j

Docker

Kubernetes

CI/CD

AWS

GCP

Azure

Tools

Docker

Kubernetes

CI/CD

Neo4j

Job description

Programming: Expert-level proficiency in Python (plus Go, Java, or C++ as needed).

AI Frameworks: Hands-on experience with LangChain, LlamaIndex, LangGraph, CrewAI, or AutoGen.

Data & Retrieval: Vector databases, hybrid search, document chunking, and knowledge graphs (e.g., Neo4j).

Cloud & MLOps: Containerization with Docker and Kubernetes, CI/CD pipelines, and cloud platforms like AWS, GCP, or Azure.

Observability: Production evaluation and tracing tools for monitoring model drift and output quality.

*End-to-End Delivery: Own the full lifecycle of GenAI applications from initial design and testing to cloud deployment and monitoring. [1, 2]

*Agentic Workflows: Build autonomous, goal-driven AI agents that can plan, reason, and execute multi-step workflows using tool-calling and APIs. [1]

*RAG & Knowledge Integration: Implement advanced retrieval systems, vector databases, and Graph RAG to ground AI responses in enterprise data and prevent hallucinations. [1, 2]

*System Optimization: Tune latency, throughput, cost-efficiency, and hardware utilization for large-scale LLM inference. [1]

*Governance & Safety: Enforce responsible AI standards, including data privacy compliance, automated testing, evaluation tracing, and security guardrails. [1, 2]

*Leadership: Mentor junior engineers, drive architectural best practices, and bridge the gap between technical teams and business stakeholders.

Salary Range: $80,000 to $125,000 per year