Staff AI Agent Software Engineer

About This Role

Pioneer and scale the foundational agentic capabilities of the platform, serving as a center of excellence for AI agent systems. This role involves building autonomous agents, multi-agent workflows, and operational scaffolding to ensure performance, reliability, and scalability across the organization.

Responsibilities

• Serve as the center of excellence for agentic systems, driving design, architecture, and operational maturity of AI capabilities.
• Build and maintain core infrastructure to enable squads to deploy autonomous, tool-using agents safely and quickly.
• Design CICD pipelines, simulation test harnesses, and end-to-end evaluations for robust agent quality and delivery.
• Architect scalable, cost-efficient, and resilient agent infrastructure supporting agnostic model use and cloud-native deployment.
• Set technical strategy for cross-org agentic development, standardizing patterns, protocols, and interfaces.
• Write highly reliable, observable, and testable code for agentic systems.
• Champion automated evaluation and regression testing for agent behavior, hallucination risks, and prompt reliability.
• Optimize agent systems for performance, latency, and cost.
• Identify and lead remediation efforts for technical debt, systemic risks, and bottlenecks in the agentic stack.
• Mentor engineers across squads in agent design, evaluation, and architecture.

Requirements

• 7+ years software engineering experience with large-scale distributed systems, AI/ML applications, or production-grade platform engineering.
• Deep experience with autonomous agents, LLM orchestration, or multi-agent systems.
• Fluency in backend languages such as Python, Node.js, or Go.
• Production experience implementing agentic systems using custom or open source frameworks and MCP for tools.
• Strong skills in cloud-native development on AWS/GCP, with infrastructure-as-code (CDK, Terraform).
• Hands-on experience with CICD, observability tooling, and automated evaluation for ML/LLM pipelines.

Qualifications

• 7+ years software engineering experience with exposure to large-scale distributed systems, AI/ML applications, or production-grade platform engineering.

Nice to Have

• Experience working in a tech company or high-growth startup.
• Experience building and shipping production agentic systems in consumer or enterprise products.
• Strong understanding of feedback loops, alignment strategies, and multi-step planning in autonomous agents.
• Contributions to open-source AI tools or frameworks.
• Production experience of developing agentic systems using multiple approaches to architecture.
• Experience integrating AI systems into traditional product stacks with real users.
• Passion for safety, interpretability, and governance in LLM-driven systems.
• Willingness to contribute outside of core expertise to drive impactful work forward.
• Developing infrastructure as code in Go.
• Familiarity with agile development methodologies (Scrum/Kanban, JIRA).
• Experience with pair programming and collaborative development techniques.
• Active contributions to open-source projects or participation in developer communities.

Skills

* Required skills

Benefits