Senior ML Engineer (Token Factory)

The Senior ML Engineer (Token Factory) at Nebius will contribute to building a high-performance inference and fine-tuning platform for large language models. The role involves identifying bottlenecks, implementing speculative decoding architectures, optimizing generative inference, and designing low-precision training and inference pipelines. You will work on GPU-accelerated systems, with a focus on throughput, latency, and cost-per-token across thousands of GPUs. You will profile GPU workloads, understand memory hierarchies, and work with modern deep learning frameworks (primarily Python). Strong communication and leadership abilities are essential, as is experience with CI/CD and unit testing. Nice-to-have items include experience with open-source inference engines, kernel languages or DSLs, and a track record of delivering products in dynamic startup-like environments. We offer competitive compensation, career growth opportunities, flexibility, and an international team. The position supports multiple locations (Amsterdam, Berlin, Israel, London, Prague) and Remote - Europe where applicable.

The text above is the employer's original job description, extracted as written. Other details on this page, like salary, responsibilities, and requirements, are interpreted from that text by our system, not values the employer explicitly confirmed, so treat them as our best interpretation rather than verified facts.