AI-ML Engineer

Greetings from TCS!!

TATA Consultancy Services is hiring for AI-ML Engineer

Desired experience range: 8+ years

Job location: Indore

Job description:

We are looking for a highly skilled and innovative AI/ML Engineer to design, develop, and deploy enterprise-grade Generative AI solutions, Multi-Agent Systems, and Retrieval-Augmented Generation (RAG) platforms on AWS Cloud. The ideal candidate will possess expertise in Python, PySpark, AWS Bedrock, LangGraph/LangChain, Vector Databases, Prompt Engineering, and LLM Orchestration.

This is a client-facing role involving the architecture and implementation of scalable AI solutions that automate complex business workflows, knowledge management systems, intelligent assistants, and enterprise digital transformation initiatives.

The candidate will be responsible for building end-to-end GenAI ecosystems including data ingestion, document processing, embedding pipelines, vector search architectures, multi-agent orchestration frameworks, evaluation mechanisms, and production-grade deployment strategies.

Key Responsibilities

Generative AI Solution Development

• Design, develop, and deploy enterprise-scale Generative AI applications using Large Language Models (LLMs).
• Develop AI-powered assistants, copilots, document intelligence systems, and workflow automation solutions.
• Build production-ready GenAI applications leveraging AWS Bedrock and foundation models.
• Implement model orchestration frameworks for complex reasoning and task execution.
• Design AI systems capable of handling structured and unstructured enterprise data.

Multi-Agent Architecture Development

• Design and implement intelligent Multi-Agent Systems using LangGraph, LangChain, CrewAI, or similar frameworks.
• Develop autonomous AI agents capable of task planning, execution, reasoning, and collaboration.
• Build agent orchestration frameworks for business process automation.
• Design supervisor-worker agent patterns and hierarchical agent architectures.
• Implement memory management and agent communication protocols.

Retrieval-Augmented Generation (RAG)

• Architect and develop enterprise RAG solutions for knowledge discovery and conversational search.
• Build document ingestion, chunking, embedding generation, and semantic retrieval pipelines.
• Develop vector search applications using ChromaDB, FAISS, Pinecone, OpenSearch, or equivalent vector databases.
• Implement hybrid search capabilities combining semantic search and keyword-based retrieval.
• Optimize retrieval quality, relevance scoring, and response grounding mechanisms.

Data Engineering & Preprocessing

• Build scalable data ingestion pipelines for structured, semi-structured, and unstructured data sources.
• Develop ETL workflows using Python and PySpark for large-scale document processing.
• Process PDFs, Word documents, emails, websites, and enterprise knowledge repositories.
• Implement document parsing, metadata extraction, data cleansing, normalization, and enrichment.
• Create embedding generation and indexing frameworks.

Prompt Engineering & Model Optimization

• Design advanced prompt engineering strategies for business-specific use cases.
• Develop prompt templates and reusable prompt libraries.
• Perform prompt tuning and contextual optimization.
• Implement token optimization strategies for cost control.
• Improve response quality, consistency, and accuracy across AI applications.