We are looking for an AI Agentic Platform Engineer to build scalable, production-ready infrastructure for LLM and multi-agent systems.

You will work at the intersection of Agentic AI, Platform Engineering, Cloud Infrastructure, Distributed Systems, and LLMOps, building the foundational platform capabilities required to develop, deploy, operate, and scale AI applications in production.

This is an engineering-heavy role suited for candidates who have moved beyond AI prototypes and have experience building and operating real production systems.

Key Responsibilities

- Build and maintain production-grade agentic AI platforms using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar technologies.
- Implement Model Context Protocol (MCP) integrations to connect AI agents with tools, services, and external APIs.
- Design agent memory and retrieval systems using vector databases, semantic caching, and Knowledge Graphs.
- Build scalable cloud-native infrastructure using Kubernetes, Docker, Helm, and serverless technologies.
- Develop and optimize LLM model-serving infrastructure, including GPU resource allocation, batching, and inference optimization.
- Build production platform services using Python, Go, or Rust.
- Implement AgentOps, evaluation, tracing, monitoring, and observability for AI systems.
- Build secure execution environments and implement RBAC, audit logging, human-in-the-loop controls, guardrails, and AI safety mechanisms.
- Implement dynamic model routing and fallback strategies to optimize cost, latency, and performance.
- Develop internal SDKs, APIs, CLI utilities, templates, and developer tooling to accelerate AI application development.




- Collaborate with AI/ML and engineering teams to establish reliable and reusable platform capabilities.

Required Qualifications

- 3+ years of experience in backend engineering, platform engineering, cloud engineering, MLOps, LLMOps, DevOps/SRE, or related areas.
- At least 1+ year of hands-on experience building production-grade LLM or agent-driven systems.
- Robust hands-on experience with Kubernetes, Docker, and Helm.
- Experience building and operating production AI/LLM infrastructure on scalable cloud platforms.
- Strong understanding of distributed systems, microservices, cloud-native architecture, and production infrastructure.
- Experience with Platform Engineering, MLOps/LLMOps, DevOps/SRE, or Microservices Architecture.
- Strong programming experience in Python, Go, or Rust.
- Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related technical field.
- Candidates should have an academic background from a Tier-1 or Tier-2 engineering institution, such as IITs, NITs, BITS, or an equivalent nationally recognized engineering institute.

Preferred Experience

- Experience with LangChain, LangGraph, AutoGen, CrewAI, or similar agent orchestration frameworks.
- Experience with MCP and tool-calling architectures.
- Experience with vLLM, TensorRT-LLM, or Ollama for model serving.
- Experience with Pinecone, pgvector, or Knowledge Graphs.
- Familiarity with LangSmith, Langfuse, Phoenix, OpenTelemetry, Ragas, DeepEval, or Braintrust.
- Experience with Firecracker, gVisor, or WASM for secure execution.
- Experience with NeMo Guardrails or Guardrails AI.
- Experience with GPU scheduling, inference optimization, model routing, evaluation pipelines, or AI safety systems.

📌 AI Agentic Platform Engineer (Chennai)
🏢 N2P Systems
📍 Chennai