ai agent engineer

Designs and delivers AI agent systems that remain reliable beyond successful demonstrations. The role combines software engineering with practical agent development, covering technical decisions and delivery from requirements and design through production operation.

• Design, build, deploy, and operate agent systems covering execution, memory, identity, tool integration, and observability within the assigned area
• Work directly with customers and stakeholders to translate needs into functional requirements and measurable acceptance criteria
• Build working prototypes and production-grade solution components from design through implementation, testing, and deployment
• Develop agent workflows and production deployments using cloud-managed AI hosting services, selecting services and development tools to meet system requirements
• Implement and operate an LLM gateway and routing layer covering model tiering, quota and cost control, and observability
• Design memory and context-management approaches for multi-step workflows, including state persistence, retrieval quality, retention, and isolation between users or engagements
• Build and maintain MCP servers and tool integrations for authorized security workflows, defining contracts, permissions, approval boundaries, and recovery behavior
• Establish automated tests and agent evaluations; distinguish model-quality issues from software defects and cover tool failures, interrupted execution, and unintended repeated actions
• Diagnose production issues using logs, metrics, and traces; improve reliability, latency, and cost; verify mitigation and recovery
• Contribute to CI/CD, release checks, rollback plans, code reviews, and technical documentation
• Mentor less experienced engineers and communicate decisions clearly to technical and non-technical stakeholders

• Substantial production software engineering experience, typically five or more years, including at least one year delivering LLM-based agents to production
• Strong programming skills and production experience in at least one general-purpose language, plus hands-on agent development using SDKs, frameworks, or direct model APIs
• Ability to independently learn an unfamiliar language or runtime and validate implementations through tests and diagnostics
• Depth in at least one technical area and ability to evaluate language, runtime, and framework trade-offs, including concurrency, performance, maintainability, and integration needs
• Experience designing systems or substantial components, evaluating alternatives, and making technical decisions independently within an agreed scope
• Practical experience with MCP, tool use, prompt and context engineering, memory, and agent evaluation, including testing multi-step behavior and failure conditions
• Practical experience with cloud-managed AI hosting services, including runtime, state, identity, integration, and observability; ability to adopt an unfamiliar platform through working implementations
• Production engineering skills in API design, asynchronous processing, persistence, authentication and authorization, observability, retries, and security boundaries
• Experience with automated testing, CI/CD, code review, and AI-assisted development; disciplined validation of generated output
• Ability to clarify requirements, communicate designs, and support the growth of other engineers
• English proficiency at B2+ level
• Будет плюсом: application security, web penetration testing or authorized red-teaming; sandboxed code execution, browser agents or autonomous tool orchestration; improving evaluation coverage, deployment safety or operating costs for agent systems; conducting technical interviews or contributing to engineering standards and knowledge sharing

• Условий в вакансии нет