AI Engineer-Production deployment experience

Role Overview

We are seeking an AI Engineer to design and deploy agentic AI systems powered by LLMs, with a

strong focus on multi-agent orchestration, reasoning workflows, and production-grade AI

platforms. This role emphasizes building autonomous, tool-using AI systems rather than

traditional model development.

Key Responsibilities:

• Agentic AI & Multi-Agent Systems
• Design and implement multi-agent architectures using LangGraph
• Build stateful, tool-augmented agents capable of reasoning, planning, and

execution

• Develop agent orchestration patterns (planner-executor, supervisor, hierarchical

agents)

• Implement memory systems (short-term, long-term, contextual memory)
• Enable cross-agent communication and coordination
• LLM Applications & Orchestration
• Build production-grade LLM applications (RAG, agents, copilots)
• Integrate tools, APIs, and enterprise systems into agent workflows
• Design robust prompting, routing, and guardrails
• Optimize workflows for latency, cost, and quality
• Platform & API Development
• Develop reusable AI services, agent frameworks, and APIs
• Contribute to AI platform capabilities (model routing, observability, guardrails)
• Cloud Deployment & Production Systems
• Deploy agent-based systems on AWS
• Use Docker and Kubernetes for scalable deployments

Information Classification: General

• Implement monitoring and observability (LangSmith)
• Ensure systems are resilient and production-ready
• Performance Optimization & Evaluation
• Evaluate agent performance across reasoning quality and task completion
• Improve workflows using feedback loops and tracing
• Diagnose and fix failure modes in multi-step pipelines
• Collaboration & Enablement
• Work with product and engineering teams to build agentic workflows
• Guide teams on best practices for agent design
• Contribute to reusable patterns and frameworks