Senior AI Inference Scientist - LLM/VLM Optimization

FDE Times

Zürich

Hybrid

CHF 150.000 - 190.000

Vollzeit

14 Tage+

Eine vollständige Bewerbung in einer Minute

Maßgeschneiderter Lebenslauf und Anschreiben – versandbereit.

Schaffe es an den ATS-Filtern vorbei

Benefits dieser Stelle

Competitive compensation
Career growth and learning
Flexibility and ownership
Collaborative and innovative culture
Impactful AI projects
International environment

Zusammenfassung

Nebius is seeking a PhD-level research scientist to advance efficient LLM and VLM inference for production systems. You will lead focused experiments, develop prototypes in PyTorch/Triton, and collaborate with MLEs and platform engineers to ship results.

You will tackle quantization, distillation, caching strategies, and multi-node serving, evaluating quality, latency, and cost per token while publishing findings and mentoring engineers.

Qualifikationen

  • A PhD in CS/ML or closely related field.
  • Strong publication record or equivalent artifacts in ML, efficient inference, or related areas.
  • Proficient in Python and PyTorch with ability to prototype ideas.
  • Deep knowledge of LLMs, VLMs, optimization, and production-serving trade-offs.
  • Excellent experimental design and analytical reasoning.
  • Strong written and verbal communication.

Aufgaben

  • Lead research projects on efficient LLM and VLM inference from hypotheses to production handoff.
  • Develop and evaluate methods: quantization, QAT, distillation, caching, and co-optimization.
  • Build prototypes with PyTorch, Triton, CUDA tooling and collaborate to production components.
  • Research routing and scheduling strategies; evaluate latency, throughput, and cost per token.
  • Investigate multi-node inference, WideEP, and expert placement trade-offs.
  • Provide rigorous evaluations on quality, stability, memory, tail latency, and token cost.
  • Share results through reports, blogs, papers; mentor engineers and scientists.

Kenntnisse

PhD in CS/ML
Publication record
Python
PyTorch
Experiment design
Communication

Ausbildung

PhD in Computer Science or ML/ML Systems

Tools

PyTorch
Triton
CUDA
TensorRT

Jobbeschreibung

Nebius is seeking a PhD-level research scientist to advance efficient LLM and VLM inference for production systems. You will lead focused experiments, develop prototypes in PyTorch/Triton, and collaborate with MLEs and platform engineers to ship results.

You will tackle quantization, distillation, caching strategies, and multi-node serving, evaluating quality, latency, and cost per token while publishing findings and mentoring engineers.

Hol dir deinen kostenlosen, vertraulichen Lebenslauf-Check.

oder ziehe deine Datei hierhin.

Similar jobs

Ähnliche Jobs, die dir auch gefallen könnten

Senior AI Inference Scientist: LLM & VLM Optimization
Senior AI Inference Scientist: LLM & VLM Optimization

Nebius Group • Zürich

Vor Ort
CHF 140.000 - 190.000
Competitive compensation
Career growth and learning机会
Flexibility and ownership
+3
Senior LLM Inference Optimization Engineer
Senior LLM Inference Optimization Engineer

FDE Times • Zürich

Hybrid
CHF 140.000 - 210.000
Competitive compensation
Career growth
Learning opportunities
+5
Senior LLM Inference & Model Optimization Scientist–Zurich
Senior LLM Inference & Model Optimization Scientist–Zurich

Nebius Group • Zürich

Hybrid
CHF 180.000 - 240.000
Competitive compensation
Career growth and learning
Flexibility and ownership
+3
Senior ML Engineer: LLM Inference & Optimization
Senior ML Engineer: LLM Inference & Optimization

Nebius Group • Zürich

Hybrid
CHF 150.000 - 190.000
Competitive compensation
Career growth and learning
Flexibility and ownership
+3
Senior Scientist, Efficient LLM Inference & Optimization
Senior Scientist, Efficient LLM Inference & Optimization

Nebius • Zürich

Vor Ort
CHF 180.000 - 250.000
Competitive compensation
Career growth and learning
Flexibility and ownership
+2
Senior Applied Scientist, Efficient LLM Inference & Model Optimization (opens in a new tab) Zurich
Senior Applied Scientist, Efficient LLM Inference & Model Optimization (opens in a new tab) Zurich

Nebius Group • Zürich

Hybrid
CHF 180.000 - 240.000
Competitive compensation
Career growth and learning
Flexibility and ownership
+3
Senior Applied Scientist, Efficient LLM Inference & Model Optimization
Senior Applied Scientist, Efficient LLM Inference & Model Optimization

FDE Times • Zürich

Hybrid
CHF 150.000 - 190.000
Competitive compensation
Career growth and learning
Flexibility and ownership
+3
Senior Applied Scientist, Efficient LLM Inference & Model Optimization
Senior Applied Scientist, Efficient LLM Inference & Model Optimization

Nebius Group • Zürich

Vor Ort
CHF 140.000 - 190.000
Competitive compensation
Career growth and learning机会
Flexibility and ownership
+3
Senior Machine Learning Engineer, LLM Inference Optimization (opens in a new tab) Zurich
Senior Machine Learning Engineer, LLM Inference Optimization (opens in a new tab) Zurich

Nebius Group • Zürich

Hybrid
CHF 150.000 - 190.000
Competitive compensation
Career growth and learning
Flexibility and ownership
+3
Senior Machine Learning Engineer, LLM Inference Optimization
Senior Machine Learning Engineer, LLM Inference Optimization

FDE Times • Zürich

Hybrid
CHF 140.000 - 210.000
Competitive compensation
Career growth
Learning opportunities
+5
Top-Standorte