Job Summary

Design and deploy LLM workflows, RAG pipelines, and agentic systems that meet enterprise security and governance requirements. Youll work on production AI systems - not demos. RAG pipelines, agent orchestration, evaluation frameworks, and integrations into existing enterprise stacks with security and compliance in mind.

Responsibilities

- Design and implement LLM workflows, RAG systems, and AI agents
- Build evaluation pipelines and monitoring for production AI features
- Integrate AI capabilities into client applications and data platforms
- Document architectures and hand off to delivery teams for scale
- Stay current on model capabilities, costs, and enterprise guardrails

Requirements

- 4+ years in software engineering with 2+ years in ML/AI




- Hands-on experience with Python and LLM APIs or frameworks
- Understanding of RAG, embeddings, and prompt engineering
- Experience shipping AI features to production environments

Nice To Have

- LangChain or similar orchestration
- Vector databases
- MLOps on AWS/Azure

Highlights

- Python LLM orchestration
- RAG evaluation
- Production MLOps

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 AI / ML Engineer (India)
🏢 Spectrum Future Technology
📍 India