Senior Software Developer: Models Team (Token Factory)

3 weeks, 5 days ago
Full-time
Senior
Software Development
Nebius

Nebius

Nebius enables B2B companies to build local hyperscaling cloud platforms with cost-effective GPUs, InfiniBand network, and 50% less compute cost. They offer managed Kubernetes and a launch-ready business model for innovative cloud solutions.

Internet Software & Services
51-250

Description

  • Onboard state-of-the-art open-source models into Nebius Token Factory.
  • Serve large language models in production with strong reliability and scale.
  • Design and operate highly scalable, highly available distributed services.
  • Build and improve advanced inference and systems optimization techniques.
  • Maintain and extend forks of inference frameworks such as vLLM and TRT-LLM.
  • Support Solutions Architects on demanding customer proof-of-concepts.
  • Develop tooling and automation for testing, rollout, diagnostics, observability, and deployment optimization.
  • Collaborate with model builders, open-source communities, Nebius Cloud teams, and hardware vendors.
  • Work closely with teams focused on cloud infrastructure, observability, reliability, fault tolerance, and platform engineering.

Requirements

  • Experience serving LLMs in production.
  • Strong programming skills in Python and/or Go.
  • Experience designing and operating highly scalable, highly available distributed services.
  • Contributions to vLLM, SGLang, TRT-LLM, or NVIDIA ecosystem open-source projects are preferred.
  • Deep understanding of KV cache management, speculative decoding, and quantization is preferred.
  • Experience with LLM evaluation frameworks is preferred.
  • Hands-on experience with performance benchmarking and optimization is preferred.
  • Deep understanding of Kubernetes is preferred.
  • Familiarity with distributed serving architectures and autoscaling is preferred.
  • Knowledge of InfiniBand, RoCE, or high-performance networking is preferred.
  • Applicants must be authorized to work in the country where they apply and provide proof of employment eligibility.

Benefits

  • Competitive compensation.
  • Career growth and learning opportunities.
  • Flexibility and ownership in how work is done.
  • Collaborative and innovative team culture.
  • Opportunity to work on impactful AI projects.
  • International environment with talented teams.
  • Remote-friendly collaboration with periodic in-person team meetups.
  • Equal opportunity employer with inclusive hiring practices.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Senior Backend Engineer, Developer Platform (Horde)

Epic Games 5K-10K Internet Software & Services

Epic Games is hiring a senior programmer for its Unreal Engine developer platform team to work on Horde, the internal platform that supports CI/CD, remote execution, build health, storage, and developer workflows.

AWS Azure C# CI/CD gRPC MongoDB .NET Redis
14 hours, 41 minutes ago

Principal Fullstack Architect (AI & Agentic Systems)

Xebia 1K-5K Internet Software & Services

Xebia is hiring a Senior AI Software Engineer for an insurance technology client to help scale an AI-native underwriting platform from MVP into a production-grade system.

AWS Azure Databricks GCP Generative AI LLM Microservices Python React Snowflake TypeScript
14 hours, 41 minutes ago

Senior Staff Back-end Engineer (eCommerce Engineering)

Coupang 1K-5K Internet Software & Services

Coupang is hiring a Senior Staff Backend Engineer to lead the architecture and technical strategy for its core e-commerce platform services across global markets.

Apache Airflow Apache Spark AWS Cassandra Grafana Java Kafka Kotlin Kubernetes Microservices OpenTelemetry Prometheus Spring
14 hours, 57 minutes ago

Autonomy Droid Perception SWE - Onboard Systems

Skyline Eco-Adventures 11-50 Hotels, Restaurants & Leisure

Zipline is hiring a Senior or Staff Perception Engineer to build and deploy real-time 3D perception systems for its autonomous drone delivery network, supporting onboard autonomy and planning for safety-critical backyard deliveries.

CNN Computer Vision Deep Learning Machine Learning
15 hours, 11 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers