Research 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

We're partnered with a well‑funded AI research company focused on building next‑generation multimodal models for media and interactive experiences. Their work spans cutting‑edge generative systems and is increasingly moving toward real‑time, interactive environments, pushing beyond static outputs into dynamic, AI‑driven applications.

This is a deeply technical, high‑impact role focused on making large‑scale AI systems faster, more efficient, and capable of running in real time. You'll work across the stack, from low‑level GPU kernels to distributed training systems, directly influencing what is computationally possible for next‑generation AI models.

What You'll Do

• Optimize training throughput across large GPU clusters, improving efficiency and utilisation
• Implement techniques such as mixed precision (FP8, BF16), memory‑efficient attention, and checkpointing
• Design and scale distributed training systems (tensor parallelism, FSDP, multi‑node setups)
• Profile and optimise inference pipelines for real‑time multimodal generation
• Improve latency through CUDA graphing, KV cache optimisation, and operator fusion
• Contribute across the stack, from kernel‑level optimisation to system‑level architecture

Requirements

• 4+ years of experience in systems engineering, ML infrastructure, or performance optimisation
• Strong experience with GPU programming (CUDA, Triton, or similar)
• Experience with distributed systems and large‑scale training (NCCL, model parallelism)
• Familiarity with ML framework internals such as PyTorch or JAX
• Experience with mixed or low‑precision techniques (FP8, INT8, BF16)
• Proven experience building and operating scalable, fault‑tolerant training systems
• Strong interest in pushing the limits of performance for cutting‑edge AI systems

Nice to Have

• Experience with compiler optimisations or model compilation (e.g., PyTorch compile)
• Background working on large multimodal or generative models
• Exposure to real‑time inference systems

If you're interested in working on the systems that enable next‑generation AI models to train faster and run in real time, this is a rare opportunity to operate at the cutting edge of research and infrastructure.