Position: Gen AI Engineer

- Location: Remote
- Work Type: Full Time
- Experience: 5–12+ Years
- Must Have: GEN AI, RAG, ,Python,React.js

Position Summary

We are seeking an exceptional Enterprise Agentic AI Engineer to design, develop, and lead the development of a production-scale Generative AI Support Platform. This role bridges contemporary LLM capabilities (RAG, multi-agent orchestration, Model Context Protocol) with legacy enterprise infrastructure, delivering autonomous customer support automation at scale.

You will implement the core pillars:

- Agentic AI orchestration (multi-agent RAG, tool calling, autonomous reasoning)
- Real-time retrieval infrastructure (sub-150ms latency, hybrid search, citation)
- Graduated governance frameworks (agentic, deterministic, human-in-the-loop automation)
- Integration with legacy APIs via Model Context Protocol (MCP)
- Production observability and safety guardrails (hallucination detection, prompt injection prevention)

Required Qualifications

- 5+ years of production backend engineering,



with 2+ years specializing in Generative AI or Agentic AI systems (LangChain, LangGraph, or equivalent frameworks).
- Hands-on expertise in Retrieval-Augmented Generation (RAG) at scale: chunking strategies, embedding models, vector databases, hybrid search (BM25 + k-NN), reranking, and citation verification.
- Deep expertise in multi-agent orchestration: designing, building, and operationalizing agentic workflows with tool calling, function calling, and structured outputs.
- Production experience with event-driven architectures: Kafka, RabbitMQ, or equivalent streaming platforms; asynchronous processing; and microservices patterns.
- Expert-level Python or Go for production systems: async I/O, FastAPI, microservices, and containerized deployment.
- Hands-on experience with React.js for building production-grade user interfaces, AI chat interfaces,

📌 Gen AI Engineer (React+ RAG) (India)
🏢 NexGen Tech Solutions
📍 India