AI Agentic Platform Engineer

Role Overview

Key Responsibilities

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

Required Skills & Qualifications

• 3+ years of backend or platform engineering experience, including at least 1+ year building production-grade LLM or agent-driven systems.
• Strong experience in Platform Engineering, MLOps/LLMOps, DevOps/SRE, or Microservices Architecture.
• Hands-on experience with production AI/LLM infrastructure and scalable cloud platforms.
• Strong understanding of cloud-native infrastructure, distributed systems, containerization, and production platform engineering.
• Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a closely related technical discipline.
• Educational background from a Tier-1 or Tier-2 engineering institution, with institutions such as IITs, NITs, BITS, or comparable nationally recognized engineering institutes preferred/expected.
• Strong engineering fundamentals with experience building and operating production systems rather than only academic or prototype-level AI projects.
• Experience with LangChain, LangGraph, AutoGen, CrewAI, or similar agent orchestration frameworks.
• Experience with vLLM, TensorRT-LLM, or Ollama for production model serving.
• Proficiency in Python, Go, or Rust for production platform services.
• Experience with Pinecone, pgvector, or Knowledge Graphs for AI memory and retrieval architectures.
• Familiarity with LangSmith, Langfuse, Phoenix, OpenTelemetry, Ragas, DeepEval, or Braintrust.
• Experience with Firecracker, gVisor, or WASM-based secure execution environments.
• Knowledge of NeMo Guardrails or Guardrails AI.
• Experience implementing GPU scheduling, batching, model routing, evaluation pipelines, or AI safety controls.

Applicants will be asked to answer the following qualifying questions when applying for this position:

• 1Do you have 3+ years of backend/platform engineering experience, including 1+ year building production LLM or agent-driven systems?
• 2Do you have hands-on production experience with Kubernetes, Docker, and Helm?
• 3Have you built and deployed production-grade AI/LLM infrastructure or agentic AI platforms?
• 4Is your Bachelor's/Master's degree from a Tier-1/Tier-2 institution such as IIT, NIT, BITS, or an equivalent institute?