GenAI & RAG AI Engineer

Tata Consultancy Services; Pennington (NJ); On-site; USD 110,000 - 125,000; Full time

Job summary

Tata Consultancy Services in Pennington, NJ seeks an Expert AI ML engineer to design and deploy enterprise GenAI applications, including RAG pipelines and vector-based search. You will drive tool-using, memory-aware prompts, and robust evaluation across cloud stacks, with a strong focus on compliance and scaling.

The role emphasizes building agentic and multi-agent workflows, data pipelines, and MLOps for production-grade AI platforms in regulated banking contexts.

Qualifications

• Expert-level Python, PySpark, and SQL proficiency.
• Experience with GenAI/LLM engineering and enterprise AI deployments.
• Strong cloud and DevOps/MLOps exposure (containers, CI/CD, pipelines).
• Knowledge of RAG, vector databases, and retrieval systems.

Responsibilities

• Design and implement enterprise-scale GenAI applications using foundation models.
• Build production-grade RAG architectures with vector search and retrieval.
• Develop AI-powered apps with prompt engineering, memory management, and tool calls.
• Optimize LLM performance, latency, and accuracy; reduce hallucinations.
• Create hybrid AI architectures integrating data sources and APIs.
• Implement guardrails and responsible AI controls.

Skills

Python

PySpark

SQL

Java

Scala

JS/TS

Tools

PyTorch

TensorFlow

Scikit-Learn

XGBoost

LightGBM

MLflow

LangChain

LangGraph

LlamaIndex

Semantic Kernel

CrewAI

AutoGen

OpenAI APIs

Gemini APIs

Claude APIs

Job description

Tata Consultancy Services in Pennington, NJ seeks an Expert AI ML engineer to design and deploy enterprise GenAI applications, including RAG pipelines and vector-based search. You will drive tool-using, memory-aware prompts, and robust evaluation across cloud stacks, with a strong focus on compliance and scaling.

The role emphasizes building agentic and multi-agent workflows, data pipelines, and MLOps for production-grade AI platforms in regulated banking contexts.