Generative AI Engineer

Tata Consultancy Services; Maharashtra; On-site; INR 2,400,000 - 6,000,000; Full time

Job summary

Tata Consultancy Services in India seeks an experienced GenAI leader to design and implement end-to-end AI solutions using LLMs and foundation models. You will build AI-powered apps, deploy RAG pipelines, and implement multi-agent systems across cloud platforms.

The role requires 8-15 years of hands-on GenAI experience, strong collaboration with stakeholders, and mentorship of engineers in a fast-evolving AI landscape.

Qualifications

• 8-15 years of experience in Generative AI and related domains.
• Experience designing end-to-end AI solutions using modern models.
• Hands-on with retrieval augmented generation and vector databases.

Responsibilities

• Design and develop end-to-end Generative AI solutions using LLMs and foundation models.
• Build AI-powered applications leveraging OpenAI, Azure OpenAI, Anthropic Claude, Gemini, Llama, Mistral, and other models.
• Develop Retrieval Augmented Generation pipelines using vector databases and knowledge retrieval frameworks.
• Implement AI agents and multi-agent systems using LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar.
• Fine-tune, evaluate, and optimize LLMs for domain-specific use cases.
• Design prompt engineering strategies to improve model accuracy, relevance, and response quality.
• Integrate AI services into enterprise platforms, APIs, web applications, and business workflows.
• Build scalable AI solutions on Azure, AWS, or Google Cloud platforms.
• Collaborate with product owners, architects, data scientists, and business stakeholders to translate requirements into AI solutions.
• Establish best practices around AI governance, security, responsible AI, and model monitoring.
• Mentor junior engineers and provide technical leadership on GenAI initiatives.
• Stay current with advancements in Generative AI, Agentic AI, and emerging AI technologies.

Skills

Generative AI

LLMs

Prompt engineering

Azure OpenAI

RAG pipelines

LangChain

Mistral

Tools

LangChain

Semantic Kernel

CrewAI

AutoGen

Job description

Experience: 8-15 Years

• Design and develop end-to-end Generative AI solutions using LLMs and foundation models.
• Build AI-powered applications leveraging OpenAI, Azure OpenAI, Anthropic Claude, Gemini, Llama, Mistral, and other advanced models.
• Develop Retrieval Augmented Generation (RAG) pipelines using vector databases and knowledge retrieval frameworks.
• Implement AI agents and multi-agent systems using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar.
• Fine-tune, evaluate, and optimize LLMs for domain-specific use cases.
• Design prompt engineering strategies to improve model accuracy, relevance, and response quality.
• Integrate AI services into enterprise platforms, APIs, web applications, and business workflows.
• Build scalable AI solutions on Azure, AWS, or Google Cloud platforms.
• Collaborate with product owners, architects, data scientists, and business stakeholders to translate requirements into AI solutions.
• Establish best practices around AI governance, security, responsible AI, and model monitoring.
• Mentor junior engineers and provide technical leadership on GenAI initiatives.
• Stay current with advancements in Generative AI, Agentic AI, and emerging AI technologies.