Job Description

Greetings from TCS!

Hiring: Generative AI Engineer / Developer

Role: Engineer / Developer

Primary Skill:Generative AI

Experience:8–10 years

Location:Bangalore

Educational Qualification:Bachelor's degree or above

Role Overview

We are looking for an experienced Generative AI Engineer/Developer to design, develop, and productionize AI-powered applications using Large Language Models (LLMs) and modern Generative AI frameworks.

The ideal candidate should have strong software engineering foundations along with hands-on experience building enterprise-grade GenAI, RAG, prompt engineering, and LLM-based solutions.

Mandatory Skills

Strong programming experience in Python.
Hands-on experience building Generative AI and LLM-based applications.
Strong understanding of Large Language Models (LLMs) and Transformer-based architectures.
Hands-on experience with RAG (Retrieval-Augmented Generation).
Experience with prompt engineering and prompt optimization techniques.
Experience with GenAI frameworks such as LangChain or LlamaIndex.
Experience working with vector databases/vector search, such as FAISS, Pinecone, Chroma, Azure AI Search, or equivalent.
Knowledge of embeddings, semantic search, chunking, retrieval, and reranking techniques.
Experience integrating LLMs through APIs and REST services.
Strong understanding of AI/ML fundamentals, model evaluation, and data preprocessing.
Experience developing scalable, production-grade applications using sound software engineering practices.
Familiarity with Git, CI/CD, testing, debugging, and deployment practices.

Key Responsibilities

Design and develop enterprise-grade Generative AI applications.
Build GenAI solutions leveraging LLMs, RAG, embeddings, and vector search.
Develop and optimize prompts for different business use cases.
Design document ingestion, chunking, indexing, retrieval, and reranking pipelines.
Integrate LLM capabilities into existing applications and APIs.
Evaluate LLM responses for accuracy, relevance, groundedness, and hallucination risk.
Implement guardrails and appropriate security controls for enterprise GenAI applications.
Optimize GenAI applications for latency, scalability, reliability, and cost.
Develop reusable AI components, APIs, and services.
Collaborate with data engineers, ML engineers, architects, and application teams to productionize GenAI solutions.
Follow coding standards, version control, testing, and CI/CD practices.

Good to Have

Experience with Azure OpenAI, AWS Bedrock, Google Vertex AI, or similar enterprise AI platforms.
Knowledge of fine-tuning, LoRA/PEFT, and model adaptation techniques.
Exposure to MLOps/LLMOps practices.
Experience with Docker and Kubernetes.
Understanding of responsible AI, LLM security, monitoring, and governance.
Experience with agentic AI or multi-agent workflows.