Jobs → Engineering → AI Platform Engineer

About the Role We are looking for a Senior AI Platform Engineer with strong experience in Generative AI, Agentic AI, LLM platforms, and enterprise AI engineering to build scalable, secure, and observable AI platform capabilities. Key Responsibilities • Design and develop enterprise AI platforms supporting Agentic AI and multi-agent orchestration • Build AI workflows integrating LLMs, agents, APIs, tools, and enterprise data sources • Implement centralized LLM/AI gateways with authentication, authorization, rate limiting, routing, and policy enforcement • Develop RAG pipelines and reusable Python-based AI services • Implement AI observability, tracing, performance monitoring, and error tracking • Build automated evaluation frameworks, feedback loops, guardrails, and agent reliability controls • Support secure, scalable production deployments and continuous improvement of AI applications Requirements • Strong experience with Python, Generative AI, LLMs, and Agentic AI • Hands-on experience with RAG and multi-agent orchestration • Experience with frameworks such as LangGraph, LangChain, or Semantic Kernel • Cloud AI experience, preferably Microsoft Azure / Azure OpenAI • Knowledge of FastAPI, REST APIs, model integrations, and enterprise application architecture • Experience with AI evaluation, observability, security, governance, and production deployment Preferred Skills • LLM gateways, model routing, rate limiting, and provider fallback • Agent harness engineering, automated evaluations, and human-in-the-loop workflows • Azure Monitor, Application Insights, OpenTelemetry, Langfuse, or LangSmith • Docker, Kubernetes, CI/CD, and infrastructure automation