> Markdown version of [/jobs/ext/3855443-staff-machine-learning-engineer](https://www.wearedevelopers.com/jobs/ext/3855443-staff-machine-learning-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Machine Learning Engineer

- **Company:** Nebius Token Factory
- **Location:** Netherlands (Remote available)
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), Nvidia CUDA, Python (Programming Language), Pytorch, Large Language Models, SGLang, Free and Open-Source Software, Ray Serve, Reasoning Engines, Triton Inference Server, TensorRT, VLLM, Decoding, KServe
- **Published:** October 22, 2026
- **Apply:** https://startup.jobs/staff-machine-learning-engineer-llm-inference-optimization-nebius-10542543

## About the Role

* Strong Python and PyTorch engineering skills.
 * Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference systems.
 * Practical knowledge of at least one modern inference stack such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or equivalent internal systems.
 * Strong understanding of transformer inference bottlenecks, including KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving.
 * Ability to reason quantitatively about latency, throughput, quality, utilization, and cost tradeoffs.
 * Strong communication skills and ability to collaborate with research, kernel, infrastructure, product, and customer teams., * Experience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, SmoothQuant, or related techniques.
 * Experience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or other inference acceleration methods.
 * Experience with agentic workloads, including tool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration.
 * CUDA or Triton familiarity, even if the role is not primarily a kernel-engineering role.
 * Open-source contributions to vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, KServe, or related projects., Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire.

## Description

* Own a platform-level optimization pillar such as quantization, speculative decoding, KV-cache optimization, engine selection, or long-context serving.
 * Create reusable evaluation, benchmarking, and rollout frameworks across multiple model families.
 * Provide technical direction to MLEs, Applied Scientists, GPU kernel engineers, and infrastructure engineers on shared performance goals.
 * Optimize LLM and VLM endpoints for latency, throughput, memory efficiency, GPU utilization, quality, and cost per token.
 * Deploy, configure, benchmark, and extend inference engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, or similar systems.
 * Build and productionize model-compression workflows, including quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery.
 * Implement or integrate speculative decoding, draft-model approaches, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving.
 * Build reproducible benchmark harnesses for TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token.
 * Partner with GPU kernel engineers and platform engineers to diagnose bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers.
 * Write clear design docs, performance reports, rollout plans, and customer-facing technical explanations.