Senior Research Engineer - Video Perception

Synthesia

Synthesia

London, UK
Posted on Nov 2, 2023

Who are we?

On a mission to make video easy for anyone …

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 push the boundaries and uncover brand new solutions to challenging problems in the AI field. 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 the domain of multiple view geometry and non-rigid motion tracking.

👩‍💼 You will join a group of more than 40 Researchers and Engineers in the R&D department. We are building a world class 4D capture facility and we want You to help us find the best way to do this! You will be working to deliver state-of-the-art solutions to track everything for humans in motion (face, body, hands, clothing, hair) in both monocular and multi-view video.

Our research is guided by our co-founders - Prof. Lourdes Agapito and Prof. Matthias Niessner. This is an open, collaborative and highly supportive environment. We are all working together to build something big - the future of synthetic media and programmable video through Generative AI. We are proud of the culture, as well as the impact of the technology we are building.

What will you be doing?

🚀 In this position, you will join our R&D team working on introducing state-of-the-art solutions for human tracking. We have built a modern volumetric capture studio with x80 24MP cameras, x300 lights, motion control platform and an amazing production crew which you will engage with on a daily basis! In this role you will:

  • Join the team to build a state-of-the-art human tracking capability.
  • Work on capturing high resolution, high fidelity, photo-real digital humans
  • Build a pipeline for accurate tracking of the face, body, hands surface of humans in motion
  • Support the production and delivery of high quality data-sets.
  • Implement data pipelines for image and geometry data processing.
  • Implement fast data processing pipelines for human tracking in multi-view video.
  • Develop production quality code to implement methods into working systems.
  • Support and develop best practises in development across the team.
  • Own the full lifecycle from concept, data, code, experiment to delivery.

Who are you?

We are looking for experienced Research Engineers, someone who knows how to deliver practical solutions and thrives working in a busy start-up environment!

If you are a domain expert on monocular and multi-view tracking, if you know the state-of-the-art and would be able to define how we address hand tracking - then we want to talk to you! We'd also love to talk to you - if this is what you dream of doing. 😎

You will have:

  • 3+ years industry experience in Computer Vision (incl. Motion Tracking). Having a related PhD is an advantage!
  • Practical Experience and strong knowledge of Geometry tracking (ideally for humans).
  • Experience in 3D computer vision and Computer graphics, you understand multiple view geometry.
  • Experience dealing with / setting up large Data-sets.
  • Excellent coding skills in Python - our teams work full-stack, you will deliver solutions from a concept to production-ready code.
  • Experience with most modern frameworks for deep learning (PyTorch) as well as for software development (Git, Linux).
  • Outstanding communication skills.

Nice to have…

  • Experience with Hand-tracking from multi-view or monocular data.
  • Experience representing Hair - hair geometry and appearance from multi-view images.
  • Experience with C++ / CUDA.

The good stuff...

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

📍 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 get 4 weeks paid sabbatical after 4 years at the company + $10,000!!

👉 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: https://www.synthesia.io/careers