Member of Technical Staff (Applied AI Engineer, Agent Capabilities)
About this role
Evaluating frontier models against real user tasks, identifying useful behaviors, and turning promising advances into production agent systems form the core daily work for this position. The team sits at the intersection of frontier AI research and product innovation, building foundational capabilities that help users and agents solve increasingly complex challenges.
Ownership spans the entire lifecycle from rapid prototyping and evaluation through launch, monitoring, and iteration. Engineers in this group improve agent planning, tool use, context management, and error recovery while collaborating closely with product management, data science, and research peers.
What you will do
- Evaluate frontier models against real user tasks to identify useful behaviors and failure modes.
- Improve agents' ability to plan, use tools, manage context, recover from errors, and complete long-running tasks reliably.
- Design scalable agent capabilities such as skills, plugins, artifact generation, and multi-agent collaboration.
- Define offline and online evaluations for task completion, correctness, safety, latency, cost, and user satisfaction.
- Build secure, observable, and reliable agent systems including permissions and safeguards for sensitive actions.
- Collaborate closely with product management, data science, and research teams to identify high-impact opportunities.
- Set technical direction on ambiguous problems through design reviews, mentorship, and technical leadership.
What you need
- Typically six or more years of professional software engineering experience with a track record of building and owning robust AI-powered products.
- Strong software engineering fundamentals with experience building and operating AI or ML products, backend services, or distributed systems at scale.
- Experience owning the AI product lifecycle including data analysis, rigorous evaluation, production monitoring, and iterative improvement.
- Practical experience in areas such as agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task execution.
- Strong product judgment and execution skills to translate ambiguous user needs into applied AI or ML solutions with measurable impact.
Nice to have
- Experience with LLM context engineering or harness engineering, subagents, coding assistants, or autonomous task execution.
- Deep familiarity with the strengths and limitations of current model families across reasoning, tool use, context management, and long-horizon tasks.
- Experience building agent permissions, safeguards, evaluation infrastructure, or production observability systems.
- Experience with mid-training, post-training, or reinforcement learning for frontier or open-source models.
- AI or ML research experience demonstrated through publications, open-source contributions, or other meaningful research impact.
- Time spent at a fast-growing startup or on a high-ownership engineering team.
Skills and tech stack
Questions candidates ask
What kind of products does the team build?
The team builds the foundations that shape how users and agents solve increasingly complex tasks. They turn frontier AI breakthroughs into reusable product capabilities and reliable, scalable experiences.
What tools and technologies are used in this role?
The tech stack includes Python, Go, Rust, PostgreSQL, DynamoDB, AWS, and TypeScript.
What level of experience is expected for applicants?
The role typically requires six or more years of professional software engineering experience with a track record of building AI-powered products, though exceptional candidates with less experience are encouraged to apply.