Product Engineer - API

TypeSafe AI•San Francisco, CA

1d•Onsite

About The Position

TypeSafe is a frontier model lab focused on building reliable and general AI systems for economically valuable automation. The company's mission is to usher in a new era of Transformative Artificial Intelligence (TAI). They are rethinking the LLM stack from first principles to build a new kind of general frontier model designed for real-world reliability, decision-making, and autonomy in production. The team is small, fast-moving, and composed of individuals from OpenAI, Google Brain, and Meta/FAIR, with backing from top-tier investors. Since mid-2024, they have been engineering the foundation for models that can achieve real-world tasks beyond the current state-of-the-art.

Requirements

Familiarity with popular frameworks and tools that can accelerate work (including coding agents), and staying current on SOTA best practices.
Ability to precisely identify the critical from the superfluous, and ruthlessly downscope.
Complete ownership – ability to think about goals on a strategic level and define what needs to happen toward that goal, rather than at the level of tasks or tickets.
Shipped software applications end-to-end, including integration with AI/LLMs, and understanding their capabilities and limitations.
Ability to think from first principles and deeply understand product and how to solve user problems in some domain.
Care deeply about our mission and are driven to translate it into real-world impact.
5+ years of professional software engineering, or equivalent professional expertise.

Responsibilities

Function as a hacker-in-residence, creating working prototypes with TypeSafe’s API to explore the frontiers of what structured LLMs can do.
Eventually take the best ideas to production.
Brainstorm innovative product applications for TypeSafe models in a writers-room style.
Create multiple unpolished working prototypes in a single day.
Refine prototypes into reliable, dependable products for end users.
Provide actionable, qualitative feedback about model performance to research teams.
Collaborate with product, marketing, platform, and solutions engineering teams to ensure the performance of applications and launch them to customers.