Genesis AI

Inference

Genesis AI  •  San Carlos, CA (Onsite)  •  7 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

What You’ll Do

  • Build low-latency inference pipelines for on-device deployment, enabling real-time next-token and diffusion-based control loops in robotics
  • Design and optimize distributed inference systems on GPU clusters, pushing throughput with large-batch serving and efficient resource utilization
  • Implement efficient low-level code (CUDA, Triton, custom kernels) and integrate it seamlessly into high-level frameworks
  • Optimize workloads for both throughput (batching, scheduling, quantization) and latency (caching, memory management, graph compilation)
  • Develop monitoring and debugging tools to guarantee reliability, determinism, and rapid diagnosis of regressions across both stacks

What You’ll Bring

  • Deep experience in distributed systems, ML infrastructure, or high-performance serving (8+ years)
  • Production-grade expertise in Python, with strong background in systems languages (C++/Rust/Go)
  • Low-level performance mastery: CUDA, Triton, kernel optimization, quantization, memory and compute scheduling
  • Proven track record scaling inference workloads in both throughput-oriented cluster environments and latency-critical on-device deployments
  • System-level mindset with a history of tuning hardware–software interactions for maximum efficiency, throughput, and responsiveness
Genesis AI

About Genesis AI

Genesis AI is a global full-stack robotics company building general-purpose robots with human-level intelligence and capabilities. Led by a world-class team obsessed with excellence at every level, Genesis AI is pushing the boundaries of robotics and AI to unlock a new era of human productivity.

We are a new generation of robotics builders, united by a shared mission to push the boundaries of physical AI. Our team brings together the minds behind many of the most significant advances in robotics and AI in recent years — spanning the full stack.

We introduced generative simulation, created foundational platforms such as Genesis, Jiminy, Flightmare, GVBD Voxels, and invented the IPC algorithm. We led the development of the first multimodal models at Mistral AI and Apple Intelligence. We co-created UMI and Diffusion Policy, pioneered reinforcement learning frameworks for superhuman drone racing, and scaled robotic data systems at NVIDIA GR00T. We built cross-platform GPU compilers such as VeriGPU, DeepCL, Coriander, and the original PyTorch. We also built industry-leading rendering engines at Google, Epic and Unity. Now, we’ve come together at Genesis AI to close the loop, and build what’s next.

Industry
Architecture & Engineering
Company Size
51-200 employees
Headquarters
Unknown
Year Founded
Unknown
Social Media