Zum Inhalt springen
kijobs

Senior Machine Learning Engineer, LLM Inference Optimization

NebiusBerlin
Entwicklung & ResearchLarge Language ModelsMachine LearningPyTorchAgentic AITransformerCUDAvLLM
Zur OriginalanzeigeDie Bewerbung läuft direkt beim Arbeitgeber.

Warum dieser Job gelistet ist

Eindeutige KI-Rollenbezeichnung im Stellentitel. Prüfverfahren ansehen

Aufgaben

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.

- 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.

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.

Anforderungen

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;

Das wird geboten

&

: - Competitive compensation - Career growth and learning opportunities - Flexibility and ownership - Collaborative and innovative culture - Opportunity to work on impactful AI projects - International environment and talented teams What s it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. 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. If you need accommodations during the application process, please let us know.

Zur Position

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.

Interesse an dieser Position?

Die vollständige Anzeige und das Bewerbungsformular liegen beim Arbeitgeber.

Zur Originalanzeige

Weitere Jobs

Wie wir sortieren

Data & AI Engineer (m/w/d)

FiveSquareLinz

Konzeption und Aufbau skalierbarer Datenplattformen und Datenarchitekturen in Cloud-, On-Premises- und hybriden Umgebungen.

Entwicklung & Researchab 3.267 € / MonatVollzeit
Computer VisionGenerative AIData ScienceNLPLarge Language Models
vor 1 Woche

Lead AI Engineer oder Senior AI Software Engineer (m/w/d)

plenum AGFrankfurt am Main

plenum unterstützt Kunden in Business, IT und Veränderungskompetenz, seit über 40 Jahren und mit über 140 Mitarbeitenden in der DACH-Region.

IntegrationVollzeit, unbefristet
RAGLangChainLangGraphMachine LearningMLOps
vor 1 Woche

AI Technical Project Manager (m/w/d)

Sopra SteriaDeutschland

Sopra Steria ist eine der führenden europäischen Management- und Technologieberatungen.

Entwicklung & ResearchVollzeit
Machine LearningPyTorchTensorFlowMLOpsGenerative AI
vor 1 Woche

AI Consultant (m/w/d)

group24 AGGescher

Du berätst unsere Kunden bei Einführung und Nutzung von KI-Lösungen und identifizierst Automatisierungs- und Optimierungspotenziale.

Strategie & Management
Copilot StudioKI-LösungenCopilot
heute

Inhouse Consultant (m/w/d) Microsoft 365 & AI Solutions

EUROBAUSTOFF Handelsgesellschaft mbH & Co. KGBad Nauheim

Berät interne Teams zu Microsoft 365, automatisiert Prozesse mit Power Automate, baut KI-Agenten mit Copilot Studio und betreut die Plattformen.

IntegrationVollzeit
Azure AICopilot StudioPower AutomateCopilotMicrosoft 365
heute

AI Operations Monitor – Digital Operations & Incident Response

Lightly AGZürich · Remote

Überwacht autonome KI-Workflows in Schichten, reagiert auf Alerts, greift bei Bedarf ein und dokumentiert Vorfälle sowie Übergaben.

Entwicklung & ResearchFreelance
Machine LearningComputer VisionClaudeMonitoring autonomer KI-AgentenIncident Response
heute

Senior Data Scientist

SQUERMünchen

Own end-to-end use cases: Translate business problems into data science and machine learning solutions from problem framing to model validat

Entwicklung & Research68.000 bis 81.000 € / JahrVollzeit
Data ScienceLarge Language ModelsMachine Learning
heute

Senior Data Scientist (all genders)

Avelios MedicalMünchen

Data extraction and transformation: Develop methods and pipelines to extract, integrate, and prepare healthcare data for secondary use, ensu

Entwicklung & ResearchVollzeit
Data ScienceMachine Learning
heute

Senior Data Analyst (m/f/d)

BertelsmannVerl

We are looking for a Senior Data Analyst (m/f/d) (unlimited, full-time) Join our team at our location in Berlin, Verl or Baden-Baden – flexi

Entwicklung & ResearchVollzeit
Machine LearningData ScienceDatabricks
heute

Senior Data Analyst (m/f/d)

BertelsmannBaden-Baden

We are looking for a Senior Data Analyst (m/f/d) (unlimited, full-time) Join our team at our location in Berlin, Verl or Baden-Baden – flexi

Entwicklung & ResearchVollzeit
Machine LearningData ScienceDatabricks
heute

Senior Data Analyst (m/f/d)

BertelsmannBerlin

We are looking for a Senior Data Analyst (m/f/d) (unlimited, full-time) Join our team at our location in Berlin, Verl or Baden-Baden – flexi

Entwicklung & ResearchVollzeit
Machine LearningData ScienceDatabricks
heute

Senior Data Scientist - Applied Scientist

Vestiaire CollectiveBerlin

We are scaling our Discovery team to build the next-generation multistage composable search stack across query understanding, retrieval, per

Entwicklung & ResearchFreelance
Data ScienceMachine LearningDeep LearningPyTorchTensorFlow
heute

Staff Data Scientist – Offer Intelligence (m/f/d)

SIXTMünchen

We work at the intersection of pricing science, offer personalisation, advanced statistics, and scalable software.

Entwicklung & ResearchVollzeit
Data ScienceKubeflowEmbeddingsTransformerMachine Learning
heute

Solutions Architect

DatabricksDeutschland

At Databricks, our core principles are at the heart of everything we do; creating a culture of proactiveness and a customer-centric mindset

IntegrationVollzeit
Generative AIData ScienceMachine LearningDatabricks
heute

AI Engineer - System Integration

ÖBB-KonzernÖsterreich

im Team Du entwickelst Agentenlösungen und Prozessautomatisierungen hands-on auf der Plattform, die für den jeweiligen Use Case am besten ge

Integration56.854 bis 56.854 € / JahrVollzeit
heute

AI Engineer - Cloud & Agent Plattform

ÖBB-KonzernÖsterreich

im Team Du baust die technische Grundlage auf Azure von Grund auf, einschließlich Netzwerk, eines compliancekonformen Setups und der Plattform-Baseline.

Legal & Governance56.854 bis 56.854 € / JahrVollzeit
Large Language ModelsLLMOpsEU AI ActKI-Agenten-Frameworks
heute

Account Manager (m/f/d)

WhyBrilliant GmbHBerlin

Job Title: Account Manager (m/f/d) Location: Berlin, Germany Why this role matters Mittelstand and enterprise leaders want to harness AI to

Entwicklung & Research70.000 bis 100.000 € / Jahr
Machine LearningAgentic AI
gestern

Das waren alle 20 Jobs zu dieser Auswahl.