Infrastructure and Reliability Engineer - Developer Platform

TypeSafe AI•San Francisco, CA

8d•Onsite

About The Position

TypeSafe is a frontier model lab. We build reliable and general AI systems to power economically valuable automation. Our mission is to usher in a new era of Transformative Artificial Intelligence (TAI): technology with the power to drive a societal shift on the scale of the agricultural and industrial revolutions. While others chase benchmarks and academic puzzles, we’ve been quietly rethinking the LLM stack from first principles — building a new kind of general frontier model designed for real-world reliability, decision-making, and autonomy in production. We’re a small, fast-moving team from OpenAI, Google Brain, and Meta/FAIR, backed by top-tier investors. Since mid-2024, we’ve been engineering the foundation for what comes after the current “state-of-the-art” — a model that actually gets things done. About the Role As an ML infrastructure and reliability engineer, you will join the team responsible for building and maintaining TypeSafe’s API platform for inference. These APIs will be user facing, latency sensitive, and (once we ship) have uptime, reliability and backwards compatibility requirements. The role is wide ranging and you will wear many hats.

Requirements

Responsible, ownership-inclined, and a team player – you believe there is no such thing as "other people's code", and will complain only the normal amount about pager duty
Experience building and operating backend services at scale with continuous delivery
Experience designing resilient systems and improving on-call experience on production systems
Are excellent under pressure – especially debugging/resolving outages
Collaborate well with others on technical and product design, advocating for what you need, and adjusting specs to changing requirements and feedback
Mission aligned and excited to go all-in
Love being part of a team

Nice To Haves

Previously built big things
Detail-oriented to the point of helpful paranoia
5+ years of professional software engineering experience (3+ years of infra/backend) with a team with rigorous engineering standards
Experience with Kubernetes, cloud providers, and AWS in particular
Experience with the challenges of ML orchestration
Experienced LLMs’ capabilities and limitations from implementing them in the past

Responsibilities

Create robust infrastructure for serving inference across multiple cloud providers
Work to ensure inference infrastructure and services are reliable and have low error rates
Create and maintain infrastructure for monitoring and alerting on requests, improving our debugging and operations stance
Ramp up oncall engineers on error handling in production via playbooks, mentorship, “fire drill” exercises, etc.