Senior ML Engineer - AI Inference & Optimization

Nebius Group; Palo Alto (CA); On-site; USD 195,000 - 262,000; Full time

Benefits offered by this job

Health insurance

401(k) plan

Parental leave

Remote work reimbursement

Disability & life insurance

Job summary

Nebius is seeking a Senior Machine Learning Engineer on the Applied AI team to own model and endpoint optimization from artifacts to production. You will optimize latency, throughput, memory, and cost per token while preserving quality; collaborate with kernel and platform engineers on serving problems and benchmarking.

You will evaluate optimizations across engines like vLLM, TensorRT-LLM, Triton, and NVIDIA Dynamo, implement quantization workflows, and design scalable multi-node inference with

Qualifications

• Strong Python and PyTorch engineering skills.
• Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference.
• Practical knowledge of at least one modern inference stack (vLLM, TensorRT-LLM, Triton, NVIDIA Dynamo, Ray Serve, KServe).
• Deep understanding of transformer inference bottlenecks (KV cache, attention, memory bandwidth, batching, parallelism).
• Ability to quantify trade-offs among latency, throughput, quality, utilization, and cost.
• Experience designing distributed inference architectures (request routing, distributed scheduling, PDD, multi-node inference, or expert parallelism).
• Strong communication and collaboration across research, kernel, infrastructure, product, and customer teams.

Responsibilities

• Own optimization projects for specific model families, customer endpoints, or serving backends.
• Compare inference engines and recommend practical serving configurations.
• 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 inference 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.
• Design and improve LLM request routers and scheduling policies that balance worker utilization, latency, and KV-cache locality.
• Scale dense and mixture-of-experts inference across multiple GPU nodes with various parallelisms.
• Build reproducible benchmark harnesses measuring TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token.
• Collaborate with GPU kernel engineers 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.

Skills

Python

PyTorch

LLM inference

VLM inference

Distributed inference

Performance optimization

Tools

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

NVIDIA Dynamo

Ray Serve

KServe

Job description

Nebius is seeking a Senior Machine Learning Engineer on the Applied AI team to own model and endpoint optimization from artifacts to production. You will optimize latency, throughput, memory, and cost per token while preserving quality; collaborate with kernel and platform engineers on serving problems and benchmarking.

You will evaluate optimizations across engines like vLLM, TensorRT-LLM, Triton, and NVIDIA Dynamo, implement quantization workflows, and design scalable multi-node inference with