Real-Time AI Systems Engineer

Harnham; United States; On-site; USD 120,000 - 150,000; Full time

Job summary

Harnham is looking for a technical expert to accelerate AI systems performance for next-generation models. The role involves optimising GPU training throughput, implementing advanced techniques, and designing scalable systems. Candidates should have over 4 years of relevant experience in performance optimisation, distributed systems, and strong GPU programming skills. This is a unique opportunity to work with cutting-edge AI technology and contribute significantly to real-time systems.

Qualifications

• 4+ years of experience in systems engineering, ML infrastructure, or performance optimisation.
• Strong experience with GPU programming.
• Proven experience building scalable, fault-tolerant training systems.

Responsibilities

• Optimize training throughput across large GPU clusters.
• Implement mixed precision and memory-efficient techniques.
• Design and scale distributed training systems.
• Profile and optimise inference pipelines for real-time multimodal generation.

Skills

GPU programming (CUDA, Triton)

Performance optimisation

Distributed systems

ML framework internals (PyTorch, JAX)

Mixed or low‑precision techniques (FP8, INT8, BF16)

Job description

Harnham is looking for a technical expert to accelerate AI systems performance for next-generation models. The role involves optimising GPU training throughput, implementing advanced techniques, and designing scalable systems. Candidates should have over 4 years of relevant experience in performance optimisation, distributed systems, and strong GPU programming skills. This is a unique opportunity to work with cutting-edge AI technology and contribute significantly to real-time systems.