Senior Machine Learning Engineer, LLM Inference Optimization

Wrong label? It is open to me · It is not open to me

About this role

The Senior Machine Learning Engineer role on Nebius's Applied AI team focuses on optimizing models and inference endpoints from artifact to production, covering areas such as quantization, speculative decoding, KV-cache tuning, inference engine selection, and serving architecture to improve latency, throughput, and cost per token. The position suits an engineer comfortable with benchmarking, diagnosing performance and quality regressions, and working alongside kernel and platform teams on distributed multi-node GPU inference. A notable requirement is the ability to validate improvements through reproducible benchmarks and carry them into safe production rollouts under real workloads.

Sourced via Jobicy · HirePadi job board