Inference

Genesis AI; San Carlos (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Genesis AI is seeking an expert to build and optimize real-time inference systems for on-device and cluster deployments. You will implement low-level CUDA/Triton kernels and integrate them with high-level AI frameworks, with a focus on both throughput and latency.

You will lead design and optimization of scalable ML infrastructure, ensuring reliability, determinism, and efficient resource usage across GPU clusters and edge devices.

Qualifications

• 8+ years of experience in distributed systems, ML infrastructure, or high-performance serving.
• Production-grade Python with strong systems languages background (C++, Rust, Go).
• Low-level performance mastery in CUDA, Triton, kernel optimization, quantization, and memory/compute scheduling.

Responsibilities

• Build low-latency inference pipelines for on-device deployment in robotics.
• Design and optimize distributed inference systems on GPU clusters for high throughput.
• Implement low-level code (CUDA, Triton, custom kernels) and integrate into high-level frameworks.
• Optimize workloads for throughput and latency through batching, quantization, caching, and memory management.
• Develop monitoring and debugging tools for reliability and rapid diagnosis of regressions.

Skills

Distributed systems

Python

C++

Rust

Go

Inference scaling

Tools

CUDA

Triton

Kernel optimization

Quantization

Memory management

Compute scheduling

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