Staff / Principal Machine Learning Engineer

This is a fully remote position, open to applicants in Switzerland.

📋 Description

• Create cutting-edge real-time multimodal models along with an orchestration platform designed to handle thousands of queries per second.

• Address ambiguous challenges and devise solutions that prioritize performance, latency, and reliability as essential product features.

• Work collaboratively with international teams to develop benchmarks or prototypes that reveal in-depth insights on various projects.

• Ensure the stability of all engineering deliverables and launch products that satisfy market demands.

⛳️ Requirements

• Inference Optimization: Profound knowledge of contemporary serving frameworks and methods such as vLLM or TRT-LLM.

• Model Acceleration: Practical experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding.

• High-Performance Systems: Expertise in C++, CUDA, Rust, or highly optimized Python. You are skilled at profiling code and maximizing performance on NVIDIA GPUs.

• Distributed Systems & Scaling: Familiarity with Kubernetes, Ray, custom load balancing, multi-GPU/multi-node inference, and effectively managing thousands of concurrent connections.

• Public work: Engagement in non-trivial systems programming projects, contributions to open-source inference engines, or detailed technical documentation.

• Full-cycle ownership: Capable of taking a model from the research team, containerizing it, optimizing its serving, and ensuring reliable operation in production.

• Background: PhD in Computer Science, Physics, Mathematics, or equivalent practical experience in developing backend or ML systems.

• Professional proficiency in English (both written and spoken) is essential, as you will be collaborating daily with our leadership and engineering teams based in the US.

🏝️ Benefits

• Health insurance

• 401(k) matching

• Flexible work hours

• Paid time off

• Remote work options