Senior Software Engineer — AI Studio (Inference Platform) - Remote

Overview

Nebius is leading a new era in cloud computing to serve the global AI economy. We create the tools and resources our customers need to solve real-world challenges and transform industries, without massive infrastructure costs or the need to build large in-house AI/ML teams. Our employees work at the cutting edge of AI cloud infrastructure alongside some of the most experienced and innovative leaders and engineers in the field.

In Short

• Design and implement services that power inference for internal and external customers.
• Integrate and scale model back-ends.
• Create sophisticated request-routing logic for high-throughput, low-latency workloads.
• Fortify observability pipeline for platform stability.
• Engage in performance tuning and memory management.
• Work with multi-tenant scheduling.
• Utilize CUDA, Triton, or other kernel-level profilers.
• Collaborate with a mindset of open communication and mentoring.
• Focus on clean, test-driven code and modern CI/CD practices.
• Excitement for shaping infrastructure for multimodal AI.

Requirements

• Fluency in Python, Go, or Rust.
• Comfortable with asynchronous programming and distributed architectures.
• Experience in API design, load balancing, caching, and queuing.
• Familiarity with inference frameworks like vLLM, sglang, or ComfyUI.
• Knowledge of orchestration stacks like Kubernetes, Ray, or FastAPI.
• Collaborative mindset and mentoring capability.
• Passion for AI and ML technologies.

Benefits

• Competitive salary and comprehensive benefits package.
• Opportunities for professional growth within Nebius.
• Flexible working arrangements.
• A dynamic and collaborative work environment.