Nebius

Staff Machine Learning Engineer, LLM Inference Optimization

Brak informacji o wynagrodzeniu

SeniorZdalnie·LondynFull-time

#463346·Dodano 15 dni temu·0

Źródło: Nebius

Aplikuj teraz

Tech Stack / Keywords

Python PyTorchvLLMSGLangTensorRT-LLMTriton Inference ServerNVIDIA DynamoCUDARay ServeKServe

Podsumowanie oferty

At Nebius Token Factory, own the path from model artifact to fast, reliable, cost-efficient LLM inference endpoints. The role focuses on inference optimization, serving architecture, benchmarking, and production deployment for open-source, customer, and internally optimized models.

Wymagania

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.

Nice to have:

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.

Obowiązki

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.

Inne informacje

Applicants must be authorized to work in the country in which they apply and provide proof of employment eligibility as a condition of hire.

Nebius

3 aktywne oferty

Zobacz wszystkie oferty

Aplikuj teraz