Senior Backend Engineer, Inference Platform

📋 Description

• Shape the core inference backbone powering frontier models.
• Solve latency-critical routing, load balancing, and resource allocation.
• Work with accelerators (H100s, H200s) at global scale.
• Partner with researchers to productionize new model architectures.
• Collaborate with open source community on inference tools.
• Deep technical ownership to make models faster, cheaper, accessible.

🎯 Requirements

• 5+ years building large-scale, fault-tolerant distributed systems.
• Strong focus on efficiency, scalability, and stability.
• Deep understanding of low-level OS: multi-threading, memory, networking.
• Expert in Rust, Go, Python, or TypeScript.
• Kubernetes or container orchestration experience.
• Familiar with GPU stacks (CUDA, Triton, NCCL) and HPC.

🎁 Benefits

• Startup equity and health insurance
• Competitive benefits package
• Open-source tooling collaboration (SGLang, vLLM)
• Work with frontier models and GPUs at scale
• Research collaboration and high-impact ownership
• Mission-driven, flexible engineering culture