Senior Research Engineer - Diffusion



London, UK
Posted on Thursday, January 18, 2024

Who are we?

On a mission to make video easy for anyone …

It is an exciting time to join Synthesia as we reached a hallmark by becoming a Unicorn, having raised $90 million in Series C funding and now evaluated at $1 billion!! ✨ 🦄

Synthesia is the world’s #1 AI video generation platform. Well, it’s actually a video production studio — in a browser. As in, no cameras or film crews at all. You simply choose an avatar, enter your script in one of 60 languages, and your video is ready in minutes. In Synthesia, you can build personalised on-the-fly videos, give your chatbot a human face or run 24/7 weather channels in different languages, to name just a few of the possibilities. 🎬

We believe the future of media is synthetic, and we are on a mission to turn cameras into code and make everyone a creator. To learn more, check out our brand video that explains what we’re doing at Synthesia.

About the role

We are looking for a Research Engineer, ****with passion for working on cutting edge problems that can help us create highly realistic, emotional and life-like synthetic humans through text-to-video.

Our aim is to make video content creation available for all - not only to studio production!

🧑🏼‍🔬 You will be someone who loves to code and build working systems. You are used to working in a fast-paced start-up environment. You will have experience with the software development life cycle, from ideation through implementation, to testing and release. You will also have extensive knowledge and experience in Computer Vision domain. You will also have experience within Generative AI space (GANs, Diffusion models and the like!).

👩‍💼 You will join a group of more than 50 Engineers in the R&D department and will have the opportunity to collaborate with multiple research teams across diverse areas, our R&D research is guided by our co-founders - Prof. Lourdes Agapito and Prof. Matthias Niessner and director of Science Prof. Vittorio Ferrari.

If you know and love DALL.E, MUSE, IMAGEN, MAKE-A-VIDEO, STABLE DIFFUSION and more - and you love large data, large compute and writing clean code, then we would love to talk to you.

What will you be doing?

🚀 In this position, you'll be working at the heart of the dynamic Avatar Video Team helping with the research and development of our generative avatar performance abilities. In other terms, given conditioning signals such as audio, video or text you will be helping create models that guides the avatar’s verbal and non verbal cues. You will also help us create high quality, production ready code and take ownership of production pipelines. This would include:

  • Building libraries to accelerate the iteration speed during development (abstracting common functionality, automating tests sweeps, visualising results etc.).
  • Developing, maintaining and deploying Computer Vision algorithms and models to update our product, integrating CI/CD.
  • Taking ownership of the full ML lifecycle from concept, development, testing, validation to deployment.
  • Adapting off-the-shelf solutions for the purposes of our product.
  • Researching novel methods to solve challenging problems that haven’t addressed before.
  • Contribute to a high-quality codebase, develop tests where necessary, and participate in code reviews.
  • Writing clean and efficient code, and defining best practices both in the code base you own and in adoption of the tools you build.
  • Optimising for deployment - turning prototypes into working solutions.
  • Developing production quality software, our teams work “full stack” with the ability to deliver direct to product and impact the world.

Who are you?

  • You have a background in Computer Vision / Computer Science and 3+ years of relevant experience.
  • You have excellent coding skills in Python and you love writing clean code. You are very passionate about the software development side of things!
  • You are a git wizard and you are able to own CI/CD across the team’s repos.
  • You are interested in model deployment and serving on Cloud infrastructure (Docker / AWS).
  • You have researched / worked with Generative Models (incl. Diffusion models) - you know all the best practices and approaches.
  • You are interested in doing research, trying new things and finding out what "sticks"!
  • You are capable of building user-facing APIs that expose a range of Computer Vision features as a service.
  • You know C++ and you are not afraid to occasionally get your hands dirty with it.
  • You have excellent verbal and written communication skills and you are passionate about what you do!

Nice to have…

If you have in-depth experience in diffusion models, if you have worked with denoising diffusion, latent diffusion, pose prediction, video generation. If you love Stable Diffusion, Large video models, Human motion generation and more - then we would love to talk to you! We'd also love to talk to you - if this what you dream of doing. 😎

Nice to have tools/skills:

  • Experience with Generative models (GANs, Diffusion models etc.)
  • Experience with Web app development
  • Strong knowledge of C++.
  • Strong background in Maths.

The good stuff...

💸 You will be compensated well (salary + stock options + bonus)

🏥 Private Medical Insurance (Medical History Disregarded basis) including mental health support, dental & vision, cashback and gym discounts.

📍 You will work in a hybrid setting with an office in London

🚲 You get a cycle to work salary sacrifice scheme to commute to the office

🏝 You get 25 days of annual leave + public holidays

🥳 You will join an established company culture with regular socials and company retreats

👉 You can participate in a generous referral scheme

🚀 You will have huge opportunities for your career growth

You can see more about Who we are and How we work here: