AI Agent Engineer

General Motors•Austin, MI

1d•Hybrid

About The Position

The Role: We are seeking an AI Agent Engineer to design, build, and operationalize AI-powered agents that enhance employee productivity and decision-making in a complex enterprise environment. The ideal candidate combines strong AI/ML foundations, hands-on experience with agent frameworks, and a pragmatic approach to delivering business value in partnership with cross-functional teams. Experience with Glean (or similar enterprise AI search/assistant platforms) is a strong plus. What You'll Do: Design and develop AI agents Engineer and implement AI agents and workflows that automate and augment knowledge work. Translate business requirements into robust agent designs, including tool orchestration, routing logic, and guardrails. Prototype quickly, then harden solutions for reliability, scalability, and maintainability. AI/ML and platform integration Leverage LLMs and related AI services (e.g., retrieval-augmented generation, embeddings, vector search) to power agent capabilities. Integrate agents with enterprise systems, APIs, and data sources (e.g., collaboration tools, knowledge repositories, ticketing systems). Partner with platform teams (e.g., Glean, M365, internal APIs) to ensure secure and compliant integrations. Agent lifecycle management Define and implement monitoring, logging, and feedback loops to continuously improve agent performance. Establish and maintain evaluation frameworks, metrics, and test harnesses for AI agent behavior and output quality. Document agent architectures, decision logic, and dependencies for support and future enhancements. Collaboration and ways of working Collaborate closely with engineers, architects, data teams, and business SMEs in a highly matrixed, global environment. Contribute to shared patterns, reusable components, and best practices for AI agent development. Champion responsible AI, including security, privacy, compliance, and user trust considerations.

Requirements

Bachelor’s degree in Computer Science, Engineering, Data Science, or related field; or equivalent practical experience.
3–7+ years of professional software engineering or AI/ML engineering experience in complex, enterprise environments.
Strong proficiency in at least one modern programming language (e.g., Python, TypeScript/JavaScript, Java).
Hands-on experience with LLM-based applications, AI frameworks, or agent tooling (e.g., LangChain, Semantic Kernel, custom orchestration frameworks).
Solid understanding of Prompt engineering and retrieval-augmented generation (RAG), RESTful APIs and integration patterns, and Data structures, algorithms, and basic ML/LLM concepts.
Experience building production services (microservices or serverless) with appropriate observability and testing.

Nice To Haves

Experience with Glean or similar enterprise AI search/assistant platforms (e.g., integrating sources, configuring tools, designing agents or workflows within the platform).
Experience with Microsoft 365 and AI assistants (e.g., Copilot) or other enterprise collaboration ecosystems.
Familiarity with Enterprise identity and access management concepts (e.g., RBAC, least privilege), Observability and telemetry for AI systems (e.g., logging, tracing, quality dashboards), and experimentation and A/B testing for AI features.
Background in user-centric design or close collaboration with UX teams for AI experiences.

Responsibilities

Design and develop AI agents
Engineer and implement AI agents and workflows that automate and augment knowledge work.
Translate business requirements into robust agent designs, including tool orchestration, routing logic, and guardrails.
Prototype quickly, then harden solutions for reliability, scalability, and maintainability.
Leverage LLMs and related AI services (e.g., retrieval-augmented generation, embeddings, vector search) to power agent capabilities.
Integrate agents with enterprise systems, APIs, and data sources (e.g., collaboration tools, knowledge repositories, ticketing systems).
Partner with platform teams (e.g., Glean, M365, internal APIs) to ensure secure and compliant integrations.
Define and implement monitoring, logging, and feedback loops to continuously improve agent performance.
Establish and maintain evaluation frameworks, metrics, and test harnesses for AI agent behavior and output quality.
Document agent architectures, decision logic, and dependencies for support and future enhancements.
Collaborate closely with engineers, architects, data teams, and business SMEs in a highly matrixed, global environment.
Contribute to shared patterns, reusable components, and best practices for AI agent development.
Champion responsible AI, including security, privacy, compliance, and user trust considerations.