Senior Machine Learning Engineer, LLM Inference Optimization

About Nebius

Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.

The role

As a Senior Machine Learning Engineer on

the Applied AI team at Nebius Token Factory,

you will own model and endpoint optimization from model artifacts through production deployment. Your work will span model internals,

quantization and model compression, speculative decoding, KV-cache optimization,

inference engines, serving architecture, and

benchmarking to improve

latency, throughput, memory efficiency, GPU utilization, and cost per token while

preserving

quality and reliability. You

will work with kernel and platform

engineers to investigate serving problems, compare configurations, and

resolve performance and quality

regressions. You will evaluate model- and engine-level optimizations together with distributed inference designs, including request routing, scheduling, prefill/decode coordination, and multi-node GPU execution. Your improvements will be validated through

reproducible benchmarks and safe production

rollouts under real-world workloads. Your responsibilities Own optimization

projects

for specific model families, customer endpoints, or serving backends. Compare inference engines

and recommend serving configurations

suited to individual

workloads. Diagnose model-quality and

performance regressions during production rollouts. Improve

LLM and VLM

endpoint

latency, throughput, memory efficiency, GPU utilization, quality, and cost per token. Deploy, configure, benchmark, and extend engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server,

and NVIDIA Dynamo. Develop production model-compression workflows covering

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.

For prefill–decode disaggregation (PDD), evaluate KV-cache transfer, worker placement, and capacity balancing to determine which workloads benefit from the architecture. Design and improve LLM request routers and scheduling policies that balance worker utilization, queueing, request characteristics, and KV-cache locality while meeting latency and reliability targets. Scale dense and mixture-of-experts inference across multiple GPU nodes. Select and tune tensor, pipeline, data, and expert parallelism—including wide expert parallelism (WideEP)—with attention to hardware topology, expert load balance, and communication overhead. Build reproducible benchmark harnesses

measuring

TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token.

Validate architecture choices under representative traffic and consistent GPU budgets. Collaborate

with GPU kernel and platform engineers to

trace

bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers. Produce design documents,

performance reports, rollout plans, and customer-facing technical explanations. Must-haves Strong

engineering skills in Python and PyTorch. Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer

inference. Practical knowledge of at least one modern inference

stack,

such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or

an equivalent internal system. A strong

understanding of transformer inference

bottlenecks involving

KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving. Ability to

quantify trade-offs among

latency, throughput, quality, utilization, and

cost. Experience designing or optimizing distributed inference system architecture, with hands-on work in one or more areas such as request routing, distributed scheduling, PDD, multi-node inference, or expert parallelism. Strong communication and

collaboration skills across

research, kernel, infrastructure, product, and customer teams. Nice-to-haves Experience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, or

SmoothQuant. Experience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or

related

inference acceleration methods. Experience

supporting agentic workloads involving

tool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration. Familiarity with CUDA or Triton; the role does not require kernel engineering to be the candidate’s primary specialization. Contributions to open-source projects such as

vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, or

KServe. Implementation experience with cache-aware request routing, PDD, or WideEP, including diagnosing communication bottlenecks and load imbalance. Familiarity with GPU communication libraries and interconnects, such as NCCL, NVLink, InfiniBand, or RoCE.

Benefits

& Perks: Competitive compensation Career growth and learning opportunities Flexibility and ownership Collaborative and innovati