Description
No description provided.
Responsibilities
•Lead solution design across agent execution, memory, identity, tool integration, and observability
•Translate customer needs into clear requirements, compare alternatives, and explain the business and technical reasons for the chosen approach
•Guide the team's use of cloud-managed AI hosting services, including Bedrock, Azure AI Foundry, and Vertex AI
•Establish implementation patterns and validate platform choices against reliability, security, cost, and operational requirements
•Design and guide implementation of an LLM gateway and routing layer covering model tiering, quota and cost control, and observability
•Design and review memory, context, and state-management approaches for long-running workflows, including recovery, data retention, access boundaries, and isolation between users or engagements
•Set integration standards for MCP servers and tools used in authorized security workflows, including reconnaissance, scanners, controlled exploit tooling, and internal services
•Define permissions, approval requirements, auditability, and failure containment
•Establish a balanced testing and evaluation strategy covering software correctness, agent behavior, security boundaries, and operational performance
•Define release criteria and ensure the team can demonstrate they are met
•Guide production readiness and incident response, including observability, cost controls, staged delivery, rollback, and recovery
•Use operational evidence to prioritize improvements and technical debt
•Plan and prioritize technical delivery with product, security, and engineering stakeholders
•Break work into achievable milestones, delegate ownership, manage dependencies, and resolve technical and delivery impediments
•Build working prototypes and production-grade solution slices, taking them through implementation, testing, and deployment
•Lead complex troubleshooting and develop engineers through design reviews, coaching, and constructive feedback
•Improve engineering processes, contribute to technical hiring, and clearly communicate progress, risks, alternatives, and decisions to customers and the team
Requirements
•Substantial experience delivering and operating production software, typically five or more years, including at least one year shipping LLM-based agents to production
•Demonstrated technical leadership and team delivery
•Strong programming skills and production depth in at least one general-purpose language, with practical agent development experience
•Ability to work across language boundaries, guide technology choices, and help the team adopt unfamiliar tools
•Ability to deliver working prototypes and production-grade implementations
•Experience designing system components or complete solutions, evaluating architectural alternatives, and making decisions based on business needs and non-functional requirements
•Deep experience with cloud-managed AI hosting services, including runtime, state, identity, integration, and observability concerns, and evidence of leading a team through adoption of an unfamiliar platform
•Practical expertise in MCP, tool orchestration, context and memory management, and agent evaluation, supported by a strong understanding of distributed-system failures and security boundaries
•Experience establishing or improving testing, CI/CD, observability, and engineering practices, and explaining how these practices improved quality, delivery, or operational outcomes
•Experience leading technical discussions with customers, presenting alternatives, and aligning stakeholders on scope, priorities, risks, and trade-offs
•Ability to plan team delivery, delegate effectively, resolve disagreements and impediments, mentor engineers, and conduct technical interviews
•Sound judgment when adopting AI development tools, with clear expectations for data access, permissions, review, and verification, and outcomes assessed through evidence
•English proficiency at B2 level or higher
Nice to have
•Experience leading engineering work in application security, penetration testing, red-teaming, or security automation within an authorized scope
•Experience designing platforms for sandboxed code execution, browser agents, or autonomous tool orchestration
•Experience establishing reusable agent components, evaluation practices, or operational standards used by multiple teams
•Experience taking a new product or technical capability from initial design through launch and ongoing operation
Conditions
No conditions specified in the posting.
