Member of Technical Staff, ML Performance

Odyssey; Greater London; On-site; GBP 70,000 - 90,000; Full time

Job summary

Odyssey in Greater London seeks an experienced software engineer specializing in machine learning performance optimization. You will optimize models for real-time users, design distributed training strategies, and work with elite ML researchers. Candidates should have at least 8 years of software engineering experience, deep insights into machine learning architectures, and proficiency in PyTorch and NVIDIA optimization. This position offers autonomy in technical decisions and a chance to work with cutting-edge technology.

Qualifications

• 8+ years of software engineering experience with significant work in ML performance.
• Deep insight into modern machine learning architectures.
• Track record of owning projects end to end.
• Proficiency with PyTorch, Triton, and NVIDIA GPU ecosystems.

Responsibilities

• Optimize models for real-time use by hundreds of thousands of users.
• Design distributed training strategies for GPU clusters.
• Develop tools to identify performance bottlenecks.
• Pioneer innovative approaches to enhance performance metrics.

Skills

Software engineering

Machine learning performance optimization

Distributed training

PyTorch

NVIDIA GPU optimization

Tools

Triton

TF/JAX

Job description

Who we are

Odyssey is an AI lab pioneering general‑purpose world models: causal, multimodal systems that learn to predict and interact with the world over long horizons, while generating real‑time, interactive simulations from any starting point. This foundational technology promises to revolutionize robotics, science, healthcare, education, gaming, defense, and beyond.

What we’re looking for

We’re seeking those who are obsessed with gaining every last drop of performance from complex systems. We’re building inference infrastructure to scale to hundreds of thousands of users within a year, while also working with massive, ever‑growing datasets and models in training. Your focus will be ensuring our models deliver exceptional speed, reliability, and scalability in both the training and inference phases, optimizing efficiency to minimize TFLOPS per user and training compute cost.

What you’ll do

• Optimize models that will be used in real‑time by hundreds of thousands of users.
• Design and implement distributed training strategies to reduce training time and resource consumption on large GPU clusters.
• Partner with our elite team of ML researchers and engineers to ensure model architectures are highly performant from conception.
• Develop sophisticated tools to identify performance bottlenecks and stability issues in both training and serving environments.
• Pioneer innovative approaches, frameworks, and system designs that enhance performance metrics across our model development and inference infrastructure.
• Have significant autonomy in technical decisions.
• Use the latest‑generation GPUs.

Who you are

• 8+ years of software engineering experience, with significant work in ML performance.
• Deep insight into modern machine learning architectures with a natural instinct for performance optimization, particularly distributed training and inference.
• Track record of owning projects end to end.
• Problem‑solving mindset with the ability to acquire new skills as needed.
• Proficiency with PyTorch (or TF/JAX) and Triton as well as NVIDIA GPU ecosystems and optimization stacks.
• Highly metric‑based.