Staff Software Engineer, AI Foundations

ABOUT THE ROLE You'll own and evolve the technical foundations that power all of Gamma's AI features, building the tools and frameworks that enable engineers across the company to ship high-quality AI experiences at scale. This means developing our AI quality and correctness evals, maintaining our LLM prompt composition framework (AIJSX), establishing reliability and observability systems, and architecting model routing infrastructure. Your work will compound across every AI feature we ship. 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. WHAT YOU'LL DO - Own and evolve 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) - Ship production code while maintaining strategic perspective, focusing on high-leverage, technically challenging or architecturally complex work - Elevate engineering quality and effectiveness across the team, setting technical direction and raising the bar through code review, design feedback, and mentorship - Proactively identify opportunities and misalignment within EPD and our roadmap, helping resolve them through technical leadership - Partner with EM, PM, and cross-functional leads to set the roadmap for AI foundations and tooling - Build systems that compound and enable other engineers to ship AI features faster and with higher quality WHAT 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 COMPENSATION RANGE: The base salary for this full-time position, which spans multiple internal levels depending on qualifications, ranges between $230K - $310K plus benefits & equity. Final offer amounts are determined by multiple factors, including but not limited to experience and expertise in the requirements listed above. If you're interested in this role but you don't meet every requirement, we encourage you to apply anyway! We're always excited about meeting great people.