As a Staff Engineer focused on AI Foundations, you'll balance hands-on engineering with strategic leadership. You'll ship production code while maintaining strategic perspective, focusing on high-leverage, technically challenging work. You'll elevate engineering quality across the team through code review and mentorship, proactively identify opportunities and misalignment across our Engineering, Product, and Design teams, and partner with EM, PM, and cross-functional leads to set the roadmap. You'll bring a research-oriented approach to novel AI quality challenges.

Our team has a strong in-office culture and works in person 4–5 days per week in San Francisco. We love working together to stay creative and connected, with flexibility to work from home when focus matters most.

Your responsibilities will include:

• Owning and evolving the technical foundations for our AI features, including AI quality and correctness evals, reliability and observability, model routing, and our LLM prompt composition framework (AIJSX)
• Shipping production code while maintaining strategic perspective, focusing on high-leverage, technically challenging or architecturally complex work
• Elevating engineering quality and effectiveness across the team, setting technical direction and raising the bar through code review, design feedback, and mentorship
• Proactively identifying opportunities and misalignment within EPD and our roadmap, helping resolve them through technical leadership
• Partnering with EM, PM, and cross-functional leads to set the roadmap for AI foundations and tooling
• Building systems that compound and enable other engineers to ship AI features faster and with higher quality

You'll bring:

• 7+ years of software engineering experience with at least 1 year building with AI generative technologies
• Prior relevant experience in developer tooling or frameworks, orchestration, observability and monitoring, ML quality, evals, or data engineering
• Prompt engineering and context engineering experience with deep understanding of LLM capabilities and limitations
• Expertise architecting, building, testing, and maintaining modern complex web applications
• Research-oriented approach to problem-solving with comfort working in ambiguity and exploring novel solutions to AI quality challenges
• Exceptional attention to detail and quality obsession, caring deeply about output quality across all dimensions
• Ability to design systems that balance security, usability, and performance
• Strong communication skills and experience influencing technical strategy across teams
• High EQ with empathetic, reflective, self-aware, growth-mindset approach

The base salary for this full-time position, which spans multiple internal levels depending on qualifications, ranges between $230K - $310K plus benefits & equity.

XML job scraping automation by YubHub

This means shaping the future of how millions of users interact with AI to bring their ideas to life while establishing technical direction for our most ambitious AI initiatives.

As a Staff Engineer focused on AI Product Experiences, you'll balance hands-on engineering with strategic leadership. You'll elevate engineering quality across the team through code review, design feedback, and mentorship while proactively identifying opportunities and misalignment within EPD.

You'll bring both data-driven rigor and strong intuition to decision-making, designing systems that balance security, usability, and performance.

Our team has a strong in-office culture and works in person 4–5 days per week in San Francisco. We love working together to stay creative and connected, with flexibility to work from home when focus matters most.

Responsibilities

• Ship production code while maintaining strategic perspective, focusing on high-leverage, architecturally challenging work

• Partner with EM, PM, and cross-functional leads to set the roadmap and drive technical decision-making

• Elevate engineering quality and effectiveness, setting technical direction and raising the bar through code review and mentorship

• Proactively identify opportunities and misalignment within EPD and the roadmap, helping resolve them

• Design systems that balance security, usability, and performance while building delightful user experiences

• Operate in both data-driven, hypothesis-testing mode and act on strong intuition, switching back and forth effectively

Requirements

• 7+ years of software engineering experience with at least 1 year building with AI generative technologies (LLMs)

• Prior experience working with CRDTs/YJS, LLMs and image models, WebSockets, and streaming

• Familiarity with context engineering, agent development, and AI patterns (RAG, embeddings, subagents, tool calling)

• Deep expertise building complex, collaborative, real-time web apps with TypeScript and React

• Strong sense of craft with drive to build delightful experiences

• Strong communication skills and experience influencing technical strategy across teams

• High EQ with empathetic, reflective, self-aware, growth mindset that actively promotes psychological safety for the team

Compensation Range

The base salary for this full-time position, which spans multiple internal levels depending on qualifications, ranges between $230K - $340K plus benefits & equity.

XML job scraping automation by YubHub