Member Of Technical Staff - Model Serving / API Backend Engineer (AI)

TL;DR

Member Of Technical Staff - Model Serving / API Backend Engineer (AI): Developing and optimizing production-ready inference services for generative models with an accent on GPU performance, API scalability, and low-latency serving. Focus on bridging the gap between frontier research checkpoints and scalable production endpoints to enable rapid deployment of AI capabilities.

Location: Hybrid (Freiburg, Germany or San Francisco, USA) or Remote with a mandatory monthly in-person week at the offices

Salary: $180,000–$300,000 USD

Company

Research lab behind foundational generative technologies like Stable Diffusion and FLUX, focusing on expanding human creativity through open science.

What you will do

• Convert research checkpoints into production-ready inference services.
• Design and maintain high-performance APIs serving millions of requests.
• Optimize inference latency and throughput across GPU infrastructure.
• Build scalable serving architectures to handle unpredictable traffic.
• Implement reliability, monitoring, and observability for model-serving systems.
• Prototype and ship demos that showcase new model capabilities rapidly.

Requirements

• Experience building and operating ML inference services at meaningful scale.
• Proficiency in Python, FastAPI, and async systems.
• Expertise in GPU infrastructure, CUDA, and inference optimization.
• Experience with Docker, Kubernetes, Redis, and Postgres.
• Strong judgment regarding performance, reliability, and cost tradeoffs.
• Must be able to commit to a monthly in-person week at company offices.

Nice to have

• Experience with TensorRT, reduced precision, layer fusion, or model compilation.
• Frontend demo tooling experience (Streamlit, Gradio, React).
• CI/CD and automated testing for ML systems.
• Knowledge of security best practices for API and model serving.

Culture & Benefits

• Research-driven environment valuing deep science and beautiful products.
• Low-ego culture where the best idea wins regardless of hierarchy.
• Distributed team with a focus on meaningful in-person connection.
• Reasonable travel costs covered for monthly office visits.
• Opportunity to work on world-leading generative AI models used by millions.