Real-Time GPU Performance Engineer for Scalable AI

Harnham; California (MO); On-site; USD 120,000 - 160,000; Full time

Job summary

Harnham is seeking a systems engineer to optimize large-scale AI systems for real-time performance. You will work on cutting-edge multimodal models, improving training efficiency and system architecture.

This role requires extensive experience in GPU programming and distributed systems, where you will directly influence AI advancements. Join Harnham to contribute to the future of interactive AI systems.

Qualifications

• 4+ years of experience in systems engineering, ML infrastructure, or performance optimization.
• Strong experience with GPU programming (CUDA, Triton, or similar).
• Experience with distributed systems and large-scale training (NCCL, model parallelism).

Responsibilities

• Optimize training throughput across large GPU clusters.
• Implement techniques such as mixed precision, memory-efficient attention, and checkpointing.
• Profile and optimize inference pipelines for real-time multimodal generation.

Skills

GPU programming

Performance optimization

Distributed systems

Machine Learning frameworks

Low-precision techniques

Job description

Harnham is seeking a systems engineer to optimize large-scale AI systems for real-time performance. You will work on cutting-edge multimodal models, improving training efficiency and system architecture.

This role requires extensive experience in GPU programming and distributed systems, where you will directly influence AI advancements. Join Harnham to contribute to the future of interactive AI systems.