Generative AI Engineer

Job Title: Generative AI Engineer*

Location: Hybrid (Gurgaon, Chennai, Bangalore)

Experience:

Total Experience: 8–12 Years

Relevant Experience: 6+ Years

Notice Period:

• Immediate Joiners or candidates serving up to 15 days notice period preferred

### Must Have Skills

• LLMs

• Multi Agent Systems

• RAG Architecture

• AI Solution Evaluation

• FastAPI

• Python

Nice to Have Skills

• Docker

• CI/CD Pipelines

• MCPs

• Cloud (AWS / Azure)

Role Overview

You will be responsible for the hands-on development, coding, and deployment of AI-powered features. Your focus is on writing clean, efficient code to integrate LLMs into existing technology stacks, building robust data pipelines for RAG, and ensuring the reliability of model outputs through testing and optimization.

Key Responsibilities

• Code and integrate LLM APIs (OpenAI, Anthropic, etc.) or local models into backend services using Python and FastAPI.

• Design and implement custom MCP servers using official SDKs (Python/TypeScript) to expose internal databases, APIs, and file systems to AI agents.

• Build and maintain Retrieval-Augmented Generation (RAG) pipelines including data ingestion, text chunking, and metadata filtering.

• Manage vector databases including indexing, querying, and retrieval optimization.

• Develop, version-control, and refine prompt templates to ensure consistent structured outputs.

• Implement multi-step agent workflows using LangChain, LangGraph, CrewAI, or similar frameworks.

• Build automated test suites for AI solution evaluation, accuracy measurement, and hallucination detection.

• Implement caching, streaming responses, and token optimization techniques to improve performance and reduce latency.

• Perform data preprocessing, cleaning, and tokenization for model fine-tuning and context retrieval.

Technical Skills

• Advanced Python (Asyncio, Pydantic)

• Optional TypeScript/Node.js

• LangChain, LlamaIndex, Hugging Face Transformers

• RAG and Vector Search concepts

• SQL and handling unstructured data formats (PDFs, Markdown, JSON)

• Docker and GitHub Actions (CI/CD)

• OpenTelemetry, LangSmith, Weights & Biases

• Evaluation frameworks and guardrails

• RESTful APIs, Streaming HTTP

• MCP Server and Client architecture

• JSON-RPC

Interview Process

1. Hackerrank Test

2. Technical Interview with Client