This vacancy is archived

View similar vacancies ↓
updated 1 month ago

Senior Software Developer (AI)

Work format
remote (Global)/onsite
Work type
fulltime
Grade
senior
English
b2
Country
UK/US/Netherlands +1 more

Job description

Text:
/
TL;DR
Senior Software Developer (AI): Building a next-generation platform for high-performance AI inference and model serving with an accent on distributed systems and inference optimization. Focus on optimizing SOTA open-source models, implementing cache-aware routing, and scaling serving architectures for production workloads.

Location: Amsterdam or London, or remote within Europe or the United States. The team meets in person every one to two months at one of its locations. Applicants must be authorized to work in the country in which they apply.

Company

Nebius builds a full-stack AI cloud platform for data processing, model training, inference, and production deployment.

What you will do

  • Onboard state-of-the-art open-source models into the Token Factory platform.
  • Build and operate reliable, scalable production infrastructure for large-scale AI model serving.
  • Develop advanced inference and systems optimizations, including cache-aware routing, KV-cache offloading, disaggregated serving, and autoscaling.
  • Maintain and extend inference framework forks such as vLLM and TRT-LLM.
  • Build testing, rollout, diagnostics, observability, traffic replay, and deployment optimization tooling.
  • Collaborate with model builders, open-source communities, cloud infrastructure teams, Solutions Architects, and hardware vendors.

Requirements

  • Experience serving large language models in production.
  • Strong Python and/or Go programming skills.
  • Experience designing and operating highly scalable, highly available distributed services.
  • Ability to work from Europe or the United States, or from the Amsterdam or London locations.
  • Authorization to work in the country of application.

Nice to have

  • Contributions to vLLM, SGLang, TRT-LLM, or NVIDIA open-source projects.
  • Knowledge of KV-cache management, speculative decoding, quantization, or LLM evaluation frameworks.
  • Experience with performance benchmarking, optimization, distributed serving architectures, or autoscaling.
  • Deep Kubernetes knowledge or familiarity with InfiniBand, RoCE, and high-performance networking.

Culture & Benefits

  • Remote-oriented collaboration with regular in-person team meetings.
  • Competitive compensation and career growth opportunities.
  • Flexibility, ownership, and an outcome-driven working style.
  • Collaborative international environment with opportunities to work on impactful AI projects.