Senior Inference Architect — Low-Latency, On-Device & GPU

Genesis AI; Greater London; On-site; GBP 110,000 - 150,000; Full time

Job summary

Genesis AI is seeking an expert in distributed systems and ML infrastructure to build and optimize low-latency inference pipelines for on-device robotics. The role focuses on GPU-accelerated architectures and integrating high-performance kernels into user-friendly frameworks.

Candidates should demonstrate production-grade Python skills with a strong background in C++/Rust/Go, and a track record of scaling workloads across both on-device and cluster environments.

Qualifications

• 8+ years in distributed systems, ML infra, or high-performance serving.
• Production-grade Python with strong systems language background (C++, Rust, Go).
• Expertise in low-level optimization: CUDA, Triton, kernels, memory 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 and efficiency.
• Implement efficient low-level code (CUDA, Triton) and integrate into high-level frameworks.
• Optimize workloads for throughput and latency via batching, scheduling, and memory management.
• Develop monitoring and debugging tools to ensure reliability and rapid regression diagnosis.

Skills

Distributed systems

Python

C++/Rust/Go

Low-level performance

ML infrastructure

GPU inference

Tools

CUDA

Triton

Job description

Genesis AI is seeking an expert in distributed systems and ML infrastructure to build and optimize low-latency inference pipelines for on-device robotics. The role focuses on GPU-accelerated architectures and integrating high-performance kernels into user-friendly frameworks.

Candidates should demonstrate production-grade Python skills with a strong background in C++/Rust/Go, and a track record of scaling workloads across both on-device and cluster environments.