← All roles

Model Capabilities Engineer

TypeSafe AI· Engineering
Apply on company site
San Francisco Office$210k - $285k + equityFull-timePosted 1mo ago

About the role

Engineer focused on building data-tooling interfaces, evaluation tooling, and end-to-end model capability improvements to advance production-ready reliability of TypeSafe’s models.

Responsibilities

  • Create high-leverage datasets, products, and user interfaces that unlock new capabilities and use cases on top of our model
  • Build internal data-tooling and evaluation interfaces — fast — that make model development clearer (evaluation, debugging, data inspection)
  • Develop and own evaluation frameworks to measure quality, reliability, and emergent characteristics across model iterations
  • Run rigorous analyses and experiments to understand how data, training choices, and targeted interventions impact model behavior
  • Turn raw model outputs and data into clear, inspectable UIs — owning a domain end-to-end, with craft and judgment over simple optimization
  • Partner closely with product managers and customers to translate real-world needs into concrete model and system improvements
  • Continuously iterate, learn, and co-discover new techniques for building exceptional, trustworthy AI products

Qualifications

  • Are generalists with solid fundamentals, strong coding ability, and product intuition
  • Maintain high attention to detail and a strong bar for quality
  • Enjoy thinking beyond the code to how systems are used in the real world
  • Are scrappy and hacky, and thrive in ambiguous problem spaces — taking satisfaction in finding creative solutions
  • Don't trust LLMs blindly — they look at the reality of model generations
  • Have hands-on experience implementing LLMs and understand their capabilities and limitations

Skills

Required:Generalist software engineering with product intuitionExperience implementing LLMsData tooling and evaluation interface developmentEvaluation framework development

Benefits

  • 100% covered health insurance
  • Daily lunch and dinner
  • Visa sponsorships
  • 401K plans
Last updated Oct 20, 2026. Interested? Apply on the company site.

About TypeSafe AI

TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.

System One ModelsJevRLCDReinforcement Learning for Calibrated Decisionscalibrated decisionLLMsTypeSafe AI
Company profileWebsite

More open roles at TypeSafe AI