Staff Engineer, Model Capabilities & Data Tools

TypeSafe AI; San Francisco (CA); On-site; USD 150,000 - 250,000; Full time

Benefits offered by this job

Base salary plus equity

Job summary

TypeSafe AI, based in San Francisco, is seeking scrappy engineers to ship data‑tooling interfaces and evaluation tooling for model intelligence. You will join a small, fast team building production‑ready reliability and decision‑making in software using Python, TypeScript, Next.js, and Kubernetes.

You will own end‑to‑end workflows, turn model outputs into clear UIs, and collaborate with product managers and customers to translate real‑world needs into concrete improvements.

Qualifications

• Generalist with 2–7 years of experience, solid fundamentals, strong coding ability and product intuition.
• Hands-on experience implementing LLMs and understanding their capabilities and limitations.
• High attention to detail and a strong bar for quality.
• Enjoy thinking beyond the code to how systems are used in the real world.

Responsibilities

• Create high‑leverage datasets, products, and user interfaces that unlock new capabilities on top of our model.
• Build internal data‑tooling and evaluation interfaces — fast — for clearer model development.
• Develop and own evaluation frameworks to measure quality, reliability, and emergent behavior.
• Run rigorous analyses to understand data, training choices, and interventions on model behavior.
• Turn raw outputs into clear, inspectable UIs with end‑to‑end ownership.
• Partner with product managers and customers to translate needs into concrete improvements.
• Iterate and discover new techniques for trustworthy AI products.

Skills

Generalist

Coding ability

Product intuition

Attention to detail

Ambiguity navigation

Hands-on LLM experience

Tools

Python

TypeScript

Next.js

Tailwind CSS

Kubernetes

Claude Code

Cursor

Job description

TypeSafe AI, based in San Francisco, is seeking scrappy engineers to ship data‑tooling interfaces and evaluation tooling for model intelligence. You will join a small, fast team building production‑ready reliability and decision‑making in software using Python, TypeScript, Next.js, and Kubernetes.

You will own end‑to‑end workflows, turn model outputs into clear UIs, and collaborate with product managers and customers to translate real‑world needs into concrete improvements.