Thesis Work for generating photo realistic virtual training data for physical AI models
Vaesteras, Sweden
- Pay
- Pay not listed
- Work setting
On-site stated — work setting source
Number of students for this thesis work: Two Location: Partly on-site Physical AI models require large amounts of training data when training for a task.
Read the full posting- Employment
- Not stated
What you’ll work on
Full postingResearch different solutions of simulating robots and their ability to capture video footage en masse.
Create 3D digital twins of robot-setups using state-of-the-art techniques, such as Gaussian Splatting/Triangle Splatting, mesh generation, etc.
Evaluate performance of robots using physical AI methods, such as ACT (Action Chunking with Transformers), trained on virtually generated video reference.
From the employer’s posting
Your responsibilities: Research different solutions of simulating robots and their ability to capture video footage en masse. Create 3D digital twins of robot-setups using state-of-the-art techniques, such as Gaussian Splatting/Triangle Splatting, mesh generation, etc.
Research different solutions of simulating robots and their ability to capture video footage en masse. Create 3D digital twins of robot-setups using state-of-the-art techniques, such as Gaussian Splatting/Triangle Splatting, mesh generation, etc. Evaluate performance of robots using physical AI methods, such as ACT (Action Chunking with Transformers), trained on virtually generated video reference.
Create 3D digital twins of robot-setups using state-of-the-art techniques, such as Gaussian Splatting/Triangle Splatting, mesh generation, etc. Evaluate performance of robots using physical AI methods, such as ACT (Action Chunking with Transformers), trained on virtually generated video reference. Explore what level of fidelity is needed from a simulation to successfully train an AI model, with the objective to find a balance between speed, implementation complexity, and performance.
What you’ll bring
All qualificationsCore experience
- Experience with machine learning and AI training, preferably in the fields of AI vision systems or imitation learning.
- Knowledge about linear algebra.
Preferred experience
- Experience with 3D rendering and CAD and/or 3D modelling techniques is a plus.
- Hands-on experience with ABB industrial robots is a plus.
Qualification wording
Experience with machine learning and AI training, preferably in the fields of AI vision systems or imitation learning.
Knowledge about linear algebra.
Experience with 3D rendering and CAD and/or 3D modelling techniques is a plus.
Hands-on experience with ABB industrial robots is a plus.
Posting record
Report an errorActively hiringFirst seen by us 1 day ago, still listed, and not a repost of an earlier listing.
- Status in our records
- Live
- First seen by us
- Oct 23, 2026 · 1 day ago
- Recorded sightings
- 3
- Last seen by us
- Oct 24, 2026
These dates show when we found the listing. Check the employer’s website to confirm it is still accepting applications.
Your next step
- Have your resume and examples of relevant work ready.
- Check the listed location, eligibility and core experience before starting.
- Ask the employer about the pay range before committing time to the process.
Complete your application on abb.wd3.myworkdayjobs.com. The employer’s form will show what is required.
Already applied? Track this application
Job description
At ABB, we help industries outrun - leaner and cleaner. Here, progress is an expectation - for you, your team, and the world. As a global market leader, we’ll give you what you need to make it happen. It won’t always be easy, growing takes grit. But at ABB, you’ll never run alone. Run what runs the world.
This role sits within ABB's Robotics business, a leading global robotics company. We're entering an exciting new chapter as we’ve announced the plan for SoftBank Group to acquire ABB Robotics. SoftBank is a globally recognized technology group and investor/operator focused on AI, robotics, and next-generation computing. By joining us now, you’ll be part of a pioneering team shaping the future of robotics—working alongside world-class experts in a fast-moving, innovation-driven environment.
This Position reports to:
R&D Team LeadYour role and responsibilities
The thesis focuses on exploring the performance of physical AIs trained on virtually generated video reference.
Details:
- Period: January - June 2027
- Number of credits: 30 ECTS/högskolepoäng (hp)
- Number of students for this thesis work: Two
- Location: Partly on-site
Physical AI models require large amounts of training data when training for a task.
Your responsibilities:
- Research different solutions of simulating robots and their ability to capture video footage en masse.
- Create 3D digital twins of robot-setups using state-of-the-art techniques, such as Gaussian Splatting/Triangle Splatting, mesh generation, etc.
- Evaluate performance of robots using physical AI methods, such as ACT (Action Chunking with Transformers), trained on virtually generated video reference.
- Explore what level of fidelity is needed from a simulation to successfully train an AI model, with the objective to find a balance between speed, implementation complexity, and performance.
Qualifications for the role
- Engineering student with background in robotics, computer science, or program with similar profile.
- Experience with machine learning and AI training, preferably in the fields of AI vision systems or imitation learning.
- Knowledge about linear algebra.
- Experience with 3D rendering and CAD and/or 3D modelling techniques is a plus.
- Hands-on experience with ABB industrial robots is a plus.
More about us
Recruiting Manager Stefan Westberg, +46724613140, will answer your questions.
Positions are filled continuously. Please apply with your CV, academic transcripts, and a cover letter in English.
We look forward to receiving your application!
A Future Opportunity
Please note that this position is part of our talent pipeline and not an active job opening at this time. By applying, you express your interest in future career opportunities with ABB.
We value people from different backgrounds. Could this be your story? Apply today or visit www.abb.com to learn more about us and see the impact of our work across the globe.
Source details
Source notes
Source excerptsSelected passages from the saved posting. Check the full description for conditions and exceptions.
- Pay
No pay amount identified in the saved description.
- Location & working pattern
Vaesteras, Sweden
- Number of students for this thesis work: Two - Location: Partly on-site Physical AI models require large amounts of training data when training for a task.
- Work authorization
No clear work-authorization passage found. Eligibility is unconfirmed.
See how this role fits your experience
Add your resume to compare the role’s scope, tools and requirements with your experience.