Genesis AI

Robotics simulation and AI foundation platform

Inference Systems

Applied Machine LearningUpdated on Nov 10

Full-timeSan Carlos, CA, USANo salary listedIn-person

About the Job

Requirements

Deep experience in distributed systems, machine-learning infrastructure, or high-performance serving, with at least 8 years of experience.
Production-grade expertise in Python and a strong background in systems languages such as C++, Rust, or Go.
Low-level performance expertise in CUDA, Triton, kernel optimization, quantization, memory management, and compute scheduling.
A track record of scaling inference workloads in throughput-oriented cluster environments and latency-critical on-device deployments.
A system-level approach and experience tuning hardware-software interactions for efficiency, throughput, and responsiveness.

Responsibilities

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, improving throughput through large-batch serving and efficient resource utilization.
Implement efficient low-level code using CUDA, Triton, and custom kernels, and integrate it into high-level frameworks.
Optimize workloads for throughput through batching, scheduling, and quantization, and for latency through caching, memory management, and graph compilation.
Develop monitoring and debugging tools to ensure reliability and determinism and rapidly diagnose regressions across both stacks.

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

About the Company

Genesis AI

Robotics simulation and AI foundation platform

Genesis AI provides a unified platform that combines robotics simulation, high-fidelity rendering, physics, and foundation models to support development in robotics and AI. It operates as a platform-as-a-service and licensing option so teams can run large-scale simulations, train reinforcement learning agents, and develop generative models in realistic virtual environments where physics, geometry, rendering, and AI tooling work together. It differs from others by bringing together core capabilities from robotics simulation, real-time rendering, computational geometry, and AI model development into one cohesive platform, backed by a team with experience at Havok, Unity, Autodesk, Google, and Epic Games. Its goal is to become a foundational technology layer that speeds up robotics and AI innovation by enabling efficient simulation, testing, and model development in a single environment.

Company size: 51-200
Company stage: Seed
Total funding: $105M
Headquarters: Paris, France
Founded: 2024

Recently Posted Jobs

Explore more opportunities at Genesis AI

See more jobs