Job Location : Hyderabad / Bangalore / Chennai / Kolkata / Noida/ Gurgaon / Pune / Indore / Mumbai

Experience: 4 to 18 years

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 our existing tech stack, building robust data pipelines for RAG, and ensuring the reliability of model outputs through rigorous testing and optimization.

Key Responsibilities

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

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

• RAG Implementation: Build and maintain the "plumbing" for Retrieval-Augmented Generation—specifically coding the data ingestion scripts, text chunking logic, and metadata filtering.

• Vector DB Management: Perform day-to-day operations on vector databases (Pinecone, Milvus, etc.), including indexing, querying, and optimizing search retrieval.

• Prompt Programming: Develop, version-control, and refine complex prompt templates (using Jinja2 or similar) to ensure consistent structured outputs (JSON/YAML).

• Agent Development: Implement multi-step workflows using LangChain, LangGraph, CrewAI etc.,, focusing on tool-calling logic and error handling.

• Evaluation & Testing: Build automated test suites to detect "hallucinations" and measure accuracy using frameworks.

• Performance Tuning: Implement caching layers and streaming responses to reduce latency and improve the end-user experience; Token optimization.

• Data Pre-processing: Clean and tokenize datasets for model fine-tuning or high-quality context retrieval.

Technical Skills (The "Execution" Stack)

• Language: Advanced Python (Asyncio, Pydantic) and optional TypeScript/Node.js (for full-stack integration).

• AI Frameworks: Hands-on experience with any of LangChain, LlamaIndex, and Hugging Face Transformers. RAG and Vector search concepts.

• Data Handling: Proficiency in SQL and handling unstructured data formats (PDFs, Markdown, JSON).

• Deployment: Practical experience with Docker, GitHub Actions (CI/CD), and experience with OpenTelemetry, LangSmith, Weights & Biases etc., Understanding of evaluation/guardrails.

• MCP/API Proficiency: Deep understanding of RESTful APIs, Streaming HTTP, MCP server vs client, JSONRPC