Senior Machine Learning - AI & GPU Performance

9 Minutes ago • 3 Years +
Research Development

Job Description

Synthesia is seeking a Senior ML Performance Engineer to join their R&D Department, focusing on generative AI for creating realistic synthetic humans. This role involves optimizing large-scale model training and inference pipelines, developing high-performance solutions, and partnering with research teams to advance model performance. The engineer will work with PyTorch, CUDA/Triton, and other advanced technologies to impact solutions used by over 60,000 businesses globally.
Good To Have:
  • PhD preferred
Must Have:
  • Optimize compute resource usage (Hopper & Blackwell GPUs) for cost and time efficiency.
  • Develop customized efficient solutions for inference pipelines (CUDA/Triton kernels).
  • Introduce or enhance tooling for optimal computational performance (DL compilers, ONNX, TensorRT).
  • Drive adoption of best practices for large-model training (checkpointing, gradient accumulation, memory optimisation).
  • Introduce or enhance tooling for distributed training, performance monitoring, and logging.
  • Design and implement techniques for model parallelism, data parallelism, and mixed-precision training.
  • Keep updated on the latest research in model compression and advanced optimisation methods.
  • 3+ years of industry experience in ML engineering.
  • 2+ years experience optimising large models.
  • Experience developing CUDA/Triton kernels and optimizing models with DL compilers.
  • Great coding skills in Python and C++.
  • Experience with optimising distributed systems and distributed tools (DDP, Deepspeed, Accelerate).
  • Some experience in the video space (Diffusion models / GAN’s).
Perks:
  • Attractive compensation (salary + stock options + bonus)
  • Private Health Insurance in London
  • Hybrid work setting with an office in London
  • 25 days of annual leave + public holidays
  • Work in a great company culture with regular planning and socials at hubs
  • Generous referral scheme
  • Strong opportunities for career growth

Add these skills to join the top 1% applicants for this job

cpp
game-texts
miro-
cuda
video-editing
pytorch
python
stripe
machine-learning

Who are we?

From your everyday PowerPoint presentations to Hollywood movies, AI will transform the way we create and consume content.

Today, people want to watch and listen, not read — both at home and at work. If you’re reading this and nodding, check out our brand video.

Despite the clear preference for video, communication and knowledge sharing in the business environment are still dominated by text, largely because high-quality video production remains complex and challenging to scale—until now….

Meet Synthesia

We're on a mission to make video easy for everyone. Born in an AI lab, our AI video communications platform simplifies the entire video production process, making it easy for everyone, regardless of skill level, to create, collaborate, and share high-quality videos. Whether it's for delivering essential training to employees and customers or marketing products and services, Synthesia enables large organizations to communicate and share knowledge through video quickly and efficiently. We’re trusted by leading brands such as Heineken, Zoom, Xerox, McDonald’s and more. Read stories from happy customers and what 1,200+ people say on G2.

In February 2024, G2 named us as the fastest growing company in the world. Today, we're at a $2.1bn valuation and we recently raised our Series D. This brings our total funding to over $330M from top-tier investors, including Accel, Nvidia, Kleiner Perkins, Google and top founders and operators including Stripe, Datadog, Miro, Webflow, and Facebook.

About the role

As a ML Performance Engineer you will join a team of 40+ Researchers and Engineers within the R&D Department working on cutting edge challenges in the Generative AI space, with a focus on creating highly realistic, emotional and life-like Synthetic humans through text-to-video. Within the team you’ll have the opportunity to work on the applied side of our research efforts and directly impact our solutions that are used worldwide by over 60,000 businesses. This is an opportunity to work for a company that is impacting businesses at a rapid pace across the globe.

What will you be doing?

As a ML Performance Engineer in the AI & GPU Performance team you will contribute to the design and development of high performance solutions.You will own one or more projects for computationally optimizing large-scale model training and inference pipelines.By partnering with researchers and research teams you’ll identify high-impact initiatives and push the boundaries of model performance. You will work on re-implementing models in an efficient manner by using PyTorch and underlying technologies like CUDA/Triton, Torch compilation, etc.

This would include:

  • Evaluating, profiling and optimising compute resource usage (e.g., Hopper & Blackwell GPUs) for cost and time efficiency at training and inference times.
  • Developing customized efficient solutions for inference pipelines (CUDA/Triton kernels) as well as Introducing or enhancing tooling for achieving optimal computational performance (e.g. DL compilers, ONNX, TensorRT)
  • Driving the adoption of best practices for large-model training, including checkpointing, gradient accumulation, and memory optimisation among others.
  • Introducing or enhancing tooling for distributed training, performance monitoring, and logging (e.g., DeepSpeed, PyTorch Distributed).
  • Designing and implement techniques for model parallelism, data parallelism, and mixed-precision training
  • Keeping updated on the latest research in model compression (e.g., quantization, pruning) and advanced optimisation methods.

Who are you?

  • You are a ML engineer passionate about high performance computing.
  • You have a background in Computer Science / Engineering and 3+ years of industry experience. (PhD preferred)
  • You have worked on optimising large models for over 2 years
  • You have experience developing CUDA/Triton kernels and optimizing models with DL compilers (torch.compile)
  • You have great coding skills in Python and C++ and you care about writing clean, and efficient code.
  • You have experience with optimising distributed systems and distributed tools like DDP, Deepspeed, Accelerate or similar
  • You have some experience in the video space (Diffusion models / GAN’s).
  • You are interested in doing research, trying new things and pushing the boundaries, going beyond what's already known.

The good stuff...

  • Attractive compensation (salary + stock options + bonus)
  • Private Health Insurance in London
  • Hybrid work setting with an office in London
  • 25 days of annual leave + public holidays
  • Work in a great company culture with the option to join regular planning and socials at our hubs.
  • A generous referral scheme when you know people that are amazing for us
  • Strong opportunities for your career growth

You can see more about Who we are and How we work here: [](https://www.synthesia.io/careers)

https://www.synthesia.io/careers

#LI-MD1

Set alerts for more jobs like Senior Machine Learning - AI & GPU Performance
Set alerts for new jobs by Synthesia
Set alerts for new Research Development jobs in United Kingdom
Set alerts for new jobs in United Kingdom
Set alerts for Research Development (Remote) jobs

Contact Us
hello@outscal.com
Made in INDIA 💛💙