ML engineer, backend for foundation models

Foundation models transformed text and images. Structured data - the largest and most consequential data format in the world - stayed untouched, until now. What LLMs did for language, we're doing for tables. We pioneered tabular foundation models: TabPFN v2 was a Nature cover story, has passed 3.5M+ downloads and 7,500+ GitHub stars, and runs in production from detecting lung disease with Oxford Cancer Analytics to preventing train failures with Hitachi.

• Own the serving path end-to-end: latency, throughput, batching, memory behavior on large inputs, and cost per prediction. Our models serve through our managed API, inside customer VPCs, and as self-hosted open weights, and you’ll have an impact across the board.
• Design robust, scalable, and secure backend systems and production-grade APIs for serving our foundation models.
• Develop high-quality, maintainable code for core backend services.
• Design, deploy, and manage core infrastructure on cloud platforms, focusing on reliability, monitoring, observability, and cost-efficiency.
• Implement secure, GDPR-compliant systems, including data storage, access control, usage tracking, and quota management.
• Drive high standards for testing, CI/CD, documentation, and security within the engineering team.

• 3+ years of professional experience in machine learning and backend engineering, with a proven track record of managing production infrastructure.
• Proven experience deploying and operating machine learning models in production, with a strong understanding of how models behave and fail under real traffic.
• Strong, hands-on experience designing and building production-grade APIs and backend services.
• Significant experience building and operating services on cloud platforms, with GCP preferred.
• Strong, hands-on experience with Infrastructure as Code (IaC) using tools like Terraform.
• Significant experience with containerization and orchestration technologies (Docker, Kubernetes).
• Proficiency in Python.
• Будет плюсом: Experience building or managing infrastructure specifically for machine learning (MLOps, model serving frameworks, feature stores, data pipelines); Deep experience with inference optimization (quantization, compilation, dynamic batching, caching strategies, interplay with distributed computing); Experience with PyTorch and FastAPI specifically; Contributions to relevant open-source projects

• You'll work alongside researchers and builders who hold themselves to a very high bar - in the quality of their work and in how they work with each other. We move fast and still take the time to do things right.
• Our teams are based in Berlin, Freiburg, and New York - when you're working on something as hard as TabPFN, being in the same room matters. But great people come from everywhere, and in exceptional cases we're open to remote, which usually means frequent travel to one of our offices.
• Wherever you're based, the whole company comes together regularly for offsites to build and celebrate together.