[Skip to main content](#main-content) [OpenNash Jobs](https://jobs.opennash.com/) [Hiring report](/reports/hiring/) · [All Volvo Group jobs](https://jobs.opennash.com/companies/volvo-group/) · [Search jobs](/search/) Volvo Group · Göteborg, SE # Msc Thesis Student - Reinforcement Learning for adapting a VLA model for Autonomous Trucks Göteborg, SE Education & Training Listed on Volvo Group’s official careers site. Listed as of October 18, 2026. Check that it is still open and apply there. [Apply on Volvo Group’s careers site →](https://jobs.volvogroup.com/job/G%C3%B6teborg-Msc-Thesis-Student-Reinforcement-Learning-for-adapting-a-VLA-model-for-Autonomous-Trucks-417-15/1371085455/) [OpenNash Jobs](https://jobs.opennash.com/) / [Volvo Group](https://jobs.opennash.com/companies/volvo-group/) / Msc Thesis Student - Reinforcement Learning for adapting a VLA model for Autonomous Trucks ## Job description Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future. If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match. ### Master Thesis Proposal Closed-Loop Reinforcement Learning for adapting a Vision-Language-Action model for Autonomous Truck Driving Alpamayo is a Vision-Language-Action model trained primarily for passenger vehicle driving. Heavy-duty vehicles introduce different vehicle dynamics and tactical driving requirements. This thesis aims to adapt a passenger-car-trained Alpamayo model to specific requirements for a 40-tonne, 18–32m truck combination using closed-loop RL post-training. All post-training runs on a 128 GB unified-memory (UMA) computer. The reward function for RL targets the behaviours where cars and long combination vehicles differ from most. Heavy-duty vehicle drivers negotiate a mandatory exit – which requires several consecutive lane changes within a fixed distance – by signalling early and reducing speed as the exit approaches. These principles, together with off-tracking and larger required time gaps, shape the reward function. The tuned policy is benchmarked against the untuned passenger car baseline. The main objectives of this thesis are: Articulated closed-loop setup: Replace the car-like dynamics in AlpaSim with a tractor–semitrailer model and build exit-ramp scenarios with dense traffic. ### Reward design (car to truck gap) Shape an RL reward function for safe completion of multiple lane changes to the exit within the available distance, using the early-signaling and speed reduction near exit. ### RL post-training & evaluation Post-train the 10B policy with AlpaGym on 128 GB UMA and compare closed-loop KPIs (exit success rate, safety margins, comfort) against the untuned car baseline. The work will be carried out at Trucks Technology and Industrial (TTI), Göteborg, and is recommended for two students with a strong background in machine learning (preferably reinforcement learning) and Python. ### Thesis team this is one of three linked master theses – (1) using the car-trained models as-is by prompting, (2) closed-loop reinforcement-learning post-training, and (3) in-vehicle deployment – forming a single thesis team that meets regularly and shares simulation infrastructure and results. ### Contact persons Deepthi Pathare ### Volvo TTI mail - deepthi.pathare@volvo.com Stefan Börjesson - stefan.a.borjesson@volvo.com Morteza Haghir Chehreghani ### Chalmers mail - morteza.chehreghani@chalmers.com Duration - Jan 2027 to Jun 2027 If this sounds interesting, please send your application before 25th October 2026 We value your data privacy and therefore do not accept applications via mail. Who we are and what we believe in We are committed to shaping the future landscape of efficient, safe, and sustainable transport solutions. Fulfilling our mission creates countless career opportunities for talents across the group’s leading brands and entities. Applying to this job offers you the opportunity to join Volvo Group. Every day, you will be working with some of the sharpest and most creative brains in our field to be able to leave our society in better shape for the next generation. ​We are passionate about what we do, and we thrive on teamwork. ​We are almost 100,000 people united around the world by a culture of care, inclusiveness, and empowerment. Trucks Technology & Industrial Division hire team players who are ready to create real customer impact. Our decentralized teams work close to our customers, with speed and autonomy, to build what they truly need. Join us to collaborate on innovative, sustainable technologies that redefine how we design, build, and deliver value. Bring your curiosity, your expertise, and your collaborative energy, and together, we’ll turn bold ideas into tangible solutions for our customers and contribute to a more sustainable tomorrow. ## At a glance - Posted by the employer: Not stated - First seen by OpenNash: Oct 11, 2026 - Last checked: Oct 18, 2026 - Listed for: 7 days - Location: Göteborg, SE[Apply on Volvo Group’s careers site →](https://jobs.volvogroup.com/job/G%C3%B6teborg-Msc-Thesis-Student-Reinforcement-Learning-for-adapting-a-VLA-model-for-Autonomous-Trucks-417-15/1371085455/) ## More jobs at Volvo Group ### [MSc Thesis: Eye tracking in Extended Reality (XR) Training](https://jobs.opennash.com/companies/volvo-group/jobs/64b3cc309bd3ad4c4aae/) Göteborg, SE ### [Area Sales Manager](https://jobs.opennash.com/companies/volvo-group/jobs/7bbef63258b20d08d307/) Göteborg, SE ### [Area Sales Manager - Market Unit Nordic](https://jobs.opennash.com/companies/volvo-group/jobs/1550ae40117c22fcd737/) Göteborg, SE ### [CO₂ (vecto) Regulation Specialist - Powertrain Technology](https://jobs.opennash.com/companies/volvo-group/jobs/76e32eb459e75c56b688/) Göteborg, SE ### [Cost Engineer](https://jobs.opennash.com/companies/volvo-group/jobs/4e1643149b3200da43a2/) Göteborg, SE ## Similar jobs at other companies ### [MSc Thesis Work for: Acoustic simulation of ABB Dynafin blades](https://jobs.opennash.com/companies/abb/jobs/dd00bdfe985c611cd0fb/) ABB · Västerås, Vastmanland County, Sweden ### [MSc Thesis Work for: e‑NVH Analysis of Traction Machines](https://jobs.opennash.com/companies/abb/jobs/84e455925eca9a30caee/) ABB · Västerås, Vastmanland County, Sweden ### [Master Thesis Student in the field of Aerospace Engineering (d/f/m)](https://jobs.opennash.com/companies/airbus/jobs/2e649450dd15955ed61e/) AIRBUS · Hamburg Area ### [Senior Professional, MSC Technical Data Analyst](https://jobs.opennash.com/companies/cargill/jobs/8f292690f38657ea3e99/) Cargill · Warsaw, Poland ### [Masters Thesis student](https://jobs.opennash.com/companies/on-semiconductor/jobs/1f68ef769c0a158680ef/) ON Semiconductor · Kista, Stockholm, Sweden OpenNash lists jobs from employers’ own careers sites and does not handle applications. Dates come from the employer where stated; “first seen” and “last checked” are our own observations. OpenNash Jobs · Official listings with dates and links to the employer. [Weekly hiring report](/reports/hiring/) · [Methodology](/methodology/)