Skip to content

Ubisoft

R&D Assistant - Neural Compositing for Real-Time Graphics - INTERNSHIP (F/M/NB)

Ubisoft is hiring an R&D Assistant - Neural Compositing for Real-Time Graphics - INTERNSHIP (F/M/NB) in Bordeaux, France. Level rates it ; you can apply on Ubisoft.

Level's read on this job

  • On Level's scale, this role is Builds AI ●●●●: the job is building AI systems.
  • The posting mentions computer vision among its tools and skills.
  • Level classes it as an internship.
  • Ubisoft has 287 other open roles on Level.
  • Posted in the last few days.

AI in this role

computer-vision

Ubisoft is a global leader in gaming with teams across the world creating original and memorable gaming experiences, from Assassin’s Creed, Rainbow Six to Just Dance and more. We believe diverse perspectives help both players and teams thrive. If you’re passionate about innovation and pushing entertainment boundaries, join our journey and help create the unknown!

Ubisoft Bordeaux

Founded in 2017 by a handful of Ubisoft experts, our studio now counts over 400 talents from 20 different nationalities. Our teams contribute to some of Ubisoft’s biggest franchises: leading the production of Assassin’s Creed Mirage in 2023, working on Assassin’s Creed Shadows and the Claws of Awaji expansion, as well as unannounced projects.

Beyond our AAA productions, we also drive technological innovation within the group through our expertise in the Anvil game engine and Ubisoft’s Online Services. We have also established a dedicated R&D division, La Forge, which brings together Ubisoft engineers and academic researchers to collaborate on prototypes that support game development, particularly in the field of AI.

Rendering complex visual effects, such as refractive glass, translucent materials, smoke, and other view-dependent or volumetric phenomena, often require specialized rendering techniques, including dedicated rendering passes or ray tracing. While these methods can produce high-quality results, they can also be computationally expensive, making them challenging to integrate into real-time applications under tight performance constraints.

Recent advances in neural rendering, frame generation, and generative models open new possibilities for rethinking how such effects are produced. Rather than explicitly simulating complex light transport, neural models could learn to reconstruct or approximate the final appearance of an object from its rendered representation and surrounding image context. This suggests a new rendering paradigm in which computationally expensive visual effects could be partially replaced by learned image-space transformations.

This internship will explore neural compositing, an approach in which selected objects are rendered using simplified geometric or shading proxies and subsequently enhanced by screen-space neural models that predict their final visual appearance. The objective is to investigate whether this approach can reproduce the visual complexity of effects such as refraction, translucency, and volumetric phenomena while reducing the cost of conventional rendering techniques.

The work will involve exploring recent developments in neural rendering, neural shading, and frame generation, and investigating their potential application to real-time visual effects. Different neural compositing strategies will be considered through experimental prototypes, with an emphasis on understanding how scene information and rendered inputs can be leveraged to reconstruct complex visual phenomena.

The internship is exploratory in nature, with the aim of identifying the strengths and limitations of neural compositing and determining which classes of visual effects are best suited to this approach. The findings will help assess its potential as a complement to conventional rendering techniques and inform future research on the topic.

References

[1] DLSS 5: Generative Neural Rendering (https://research.nvidia.com/labs/adlr/DLSS5/)

[2] Generative AI model for Global Illumination effects (https://gpuopen.com/learn/genai-model-for-global-illumination/)

[3] Temporally stable generative illumination with a one-step diffusion model (https://gpuopen.com/learn/temporally-stable-generative-illumination/)

[4] An Introduction to Neural Shading (https://research.nvidia.com/labs/rtr/publication/duca2025neural/)

  • You are in the final year of an engineering degree or pursuing a research master in computer science or a related field
  • Ability to read and understand research papers
  • Strong programming skills in C++ and/or Python
  • Good Knowledge of machine learning and neural networks
  • Good Understanding of image processing or computer vision concepts
  • Basic Understanding of computer graphics and real-time rendering
  • Familiarity with diffusion models or generative models is a plus
  • Good communication skills in English, written and spoken.
  • Contract : 6 months internship from March 2027 to September 2027. An internship agreement provided by your school is mandatory.
  • Location : Bordeaux

Supervision

  • Antoine Houdard (R&D Scientist)
  • Georges Nader (R&D Scientist)

How we rate this

R&D Assistant - Neural Compositing for Real-Time Graphics - INTERNSHIP (F/M/NB) at Ubisoft rates 91 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.

Classification

Builds AI. The job is building AI systems.

  1. ●●●● Builds AI80 to 100
  2. ●●●○ Works on AI60 to 79
  3. ●●○○ Uses AI40 to 59
  4. ●○○○ Little AI0 to 39

Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.

Prepare for this job

Built from this posting and from similar jobs on Level.

Skills and AI tools this role asks for

Computer vision

Questions you could be asked

  1. Walk me through a computer vision problem you solved, from raw data to a deployed model.
  2. How would you decide a model or AI system is ready to ship?
  3. Tell me about a time a model underperformed in production. How did you find out, and what did you change?

Adapt your resume

  • List these exact terms on your resume: Computer vision. An applicant tracking system matches the wording, not the idea.
  • Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
  • Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.

Get your CV reviewed before you apply

Send your CV and the role you want next. Your review arrives by email within 3 days.

Get new AI jobs (Builds AI ●●●●) by email

One email a week, each job rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.

Free.

Similar roles

Other roles that build AI, at other companies.

What kind of AI work fits you?

Answer 12 practical questions in about three minutes. Get a simple profile, the work it points to, and live roles to explore next.

Find my next step

More jobs at Ubisoft

Related searches

Same AI level

Jobs by city