We are seeking a Lead AI Engineer to spearhead the design and deployment of autonomous agent systems built on AWS Bedrock. In this role, you will define the architecture, tooling, and operational standards for production-grade LLM agents, driving reliability, performance, and innovation across our agentic platform.
Responsibilities
- Design the architecture for building, deploying, and operating autonomous agents, including runtime, memory, identity, tools, and observability
- Lead the adoption of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deployments
- Architect long-term memory and context-management systems that hold up across multi-step engagements
- Build and curate MCP servers and tool integrations that agents call out to, including recon, scanners, exploit primitives, and custom internal services
- Drive reliability, cost, and latency of agent reasoning by setting the bar for evals, tracing, and guardrails
Requirements
- 5+ years of experience building production software, including 1+ year shipping LLM-based agents to production
- At least 1 year of relevant leadership experience
- Proficiency in Python with hands-on experience using an agentic framework such as Strands, LangGraph, or Claude Agent SDK (or equivalents like OpenAI Agents SDK or CrewAI)
- Deep familiarity with AWS Bedrock AgentCore primitives (Runtime, Memory, Identity, Gateway, Observability), or proven ability to ramp up quickly
- Practical understanding of MCP, tool use, and prompt/context engineering, along with memory architectures and agent evaluation
- Capability to design for production environments, covering observability, guardrails, and retries
- Competency in cost control and security boundaries for agent-based systems
- Proficiency in English at an Upper-Intermediate level (B2) or higher
Nice to have
- Background in application security, web pentesting, or red-teaming
- Experience with sandboxed code execution, browser agents, or autonomous tool orchestration