Agentic AI Infrastructure & Orchestration Engineer

As an AI Infrastructure Engineer, you will be responsible for architecting and deploying agentic multi-agent AI frameworks. Your key responsibilities include: - Developing scalable pipelines integrating LLM, RAG, VectorDB, and Agents. - Building and deploying MCP server for Agentic AI Agents and Integration. - Implementing observability, latency optimization, and performance monitoring systems. - Designing self-refine / feedback loop learning architectures. - Architecting multi-agent system architecture and deployment. - Integrating with frameworks such as LangGraph, CrewAI, AutoGen, or Swarm. - Developing containerized deployments (Docker / Kubernetes) for multi-agent clusters. - Building end-to-end scalable pipelines integrating LLMs, RAG, VectorDB, and Agents. - Implementing retrieval-augmented generation (RAG) architectures. - Orchestrating data movement, context caching, and memory persistence. - Building and maintaining MCP servers for Agentic AI agents. - Developing APIs, microservices, and serverless components. - Monitoring system performance and implementing optimization strategies. - Implementing self-refining / reinforcement learning feedback mechanisms. - Designing memory systems for adaptive agent learning. You should possess technical skills in: - Expert-level Python programming (async, multiprocessing, API design). - Familiarity with LLM Ecosystem and databases such as VectorDBs, NoSQL, and SQL. - Experience with Cloud Platforms like AWS, Azure, GCP, and related tools. - Knowledge of observability tools like Prometheus, Grafana, etc. - Proficiency in CI/CD, DevOps, and other tools like FastAPI, gRPC, etc. Preferred experience includes: - Designing agentic workflows or AI orchestration systems. - Background in applied AI infrastructure or ML Ops. - Exposure to RAG-based conversational AI or autonomous task delegation frameworks. Soft skills required: - Ability to translate conceptual AI architectures into production-grade systems. - Strong problem-solving and debugging capabilities. - Collaboration mindset for working with cross-functional teams. - Passion for innovation in agentic intelligence and AI autonomy. You should have a Bachelors or Masters in Computer Science, AI/ML, or related field with 5+ years of experience in backend, cloud, or AI infrastructure engineering. 2+ years in applied AI or LLM-based system development is preferred. Optional nice-to-haves include knowledge of Reinforcement Learning from Human Feedback, experience with on-premise or private LLMs, familiarity with graph-based reasoning, and understanding of AI safety and alignment.,