
AFRY · Göteborg
Senior Geometri Arkitekt – Fordon hos AFRY. Avdelning: Mechanical Engineering (Product and Machine Design). Anställningstyp: Full-time. Erfarenhetsnivå: Associa...
Senior Geometri Arkitekt – Fordon hos AFRY. Avdelning: Mechanical Engineering (Product and Machine Design). Anställningstyp: Full-time. Erfarenhetsnivå: Associate. Plats: Gothenburg, Västra Götaland County, Sweden. Ansök via SmartRecruiters.
Do you want to work with advanced computer vision algorithms that run in real vehicles shortly after your work being committed? Do you enjoy solving real-world challenges using C++, geometry, and rich sensor data from cameras and LiDAR? Are you looking for a place where your code reaches real vehicles fast, collaboration and teamwork are at the core, and your ideas help shape the future of intelligent systems and physical AI? INSIGHTS FROM THE TEAM We develop solutions for calibration, vehicle motion estimation, and precise positioning using data from cameras and LiDAR, bringing perception to life in real‑world driving scenarios. Our work blends mathematical modeling, geometric computer vision, and modern C++ with practical testing in vehicles. We continuously evaluate and refine our algorithms through performance metrics, visualization tools, and diverse real‑world datasets collected across teams. As a team, we value curiosity, collaboration, and an evidence-driven approach. We share knowledge openly, challenge ideas constructively, and focus on turning theory into robust features that run reliably on embedded systems. Working in a hybrid setup, we support each other in staying grounded, practical, and accountable while delivering results that matter. YOUR MISSION AND DAY-TO-DAY TASKS In this role, you will design, implement, and refine algorithms that improve and sharpen our perception stack. You’ll work across the full development cycle, from early concept exploration to testing in simulation, HIL setups, and real vehicles. Collaborating closely with experts in computer vision, deep learning, and platform engineering, you’ll help shape product direction while keeping performance, reliability, and safety at the core. Typical tasks on a day to day include: * Developing new and improving existing algorithms and solutions for camera and LiDAR based real-time calibration and localization. * Developing geometric computer vision algorithms, including visual odometry, calibration, localization, and 3D reconstruction. * Driving product development from proof of concept and requirements through implementation, review, integration, and testing. * Writing and reviewing production-grade C++ for safety-critical, real-time systems running on Linux. * Running experiments and evaluations in HIL environments and in-vehicle testing. * Building tools in Python to monitor, evaluate, and visualize algorithm behavior. * Reading research, building proofs of concept, and transforming findings into production-ready code. WHAT’S IN IT FOR YOU * Work with cutting-edge tech at one of Sweden’s most interesting, challenging, and innovative AI/ML companies. * Collaborate with highly skilled, innovative, creative, and smart people. * Work with people from all over the world, close to where science is becoming real-world technology. * Enjoy a flexible work approach and a genuinely good work-life balance. QUALIFICATIONS & EXPERIENCE You bring several years of experience developing algorithms in complex products, and you enjoy balancing practical engineering with solid mathematical reasoning. You thrive in collaborative environments, take initiative, and like turning ideas into measurable results. You appreciate clear communication, shared ownership, and supporting your teammates. You are comfortable navigating challenges, learning new concepts quickly, and seeing the bigger picture across system boundaries. Essential experience * Solid C++ programming skills, with the ability to write performant, testable, and maintainable code. * A background in computer vision, robotics, software engineering, computer science, electrical engineering, or a related field. * Several years of relevant industry experience, hopefully across multiple development cycles. * Experience integrating software into complex products. * Ability to work with mathematics relevant to geometric computer vision. * Demonstrated ability to apply research or theoretical ideas in practice. Nice-to‑have, but not essential * Industrial computer vision experience. * Experience in system design, requirements management, or software architecture. * Background from related industries such as robotics, aviation, defense, medical devices, automotive, trucks, construction equipment, computer graphics, or 3D game development. * Python experience for tooling and analysis. * Experience from using and evaluating deep learning models within computer vision * GPU programming (CUDA), computer graphics, or embedded software experience. * Experience with continuous integration/delivery or agile methods. * Contributions to open-source projects, publications, or personal repositories showcasing practical work. This role may have access to sensitive information, trade secrets, and confidential data. As part of the recruitment process, the selected candidate might undergo a background check. MORE ABOUT ZENSEACT Our software makes a difference. Using AI-based technology to create the ultimate driver support, we’re fighting to end car accidents and make roads safe for everyone. Every year, around 1,4 million people die in traffic while approximately 50 million people get injured. Many get disabled as a result of their injury. We can do better. One purpose, one product. We’re a software company dedicated to revolutionizing car safety. By designing the complete software stack for autonomous driving and advanced driver-assistance systems, we’re fighting to end car accidents and make roads safe for everyone. Zenseact was founded by Volvo Cars, and the teams are based in Gothenburg and Lund, Sweden and Munich in Germany. When we aim for zero accidents faster, we strive to speed up the transition to safe automation. This is essentially achieved by making cars updatable – like a computer or a phone. With regular software updates, a vehicle can be made safer long after its production. By accelerating improvement loops, shortening development cycles, and deploying high-capacity software quickly, we can make cars safer, and faster. Culture with people at heart To achieve our mission of saving lives and ending traffic accidents we must go where nobody has before. It requires us to venture into the unknown, pioneering new technology and pushing the frontier of autonomous driving. While there’s no denying our determination and expertise, we must stand united to succeed. By fostering a culture of support and enablement – a place of psychological safety where all of us can thrive – everything else will follow. We call this a people-at-heart culture. This culture means caring. It means the company cares about me, and we care about one another. It means sharing, so we give each other energy and have fun together. Our culture is also about belonging. It’s important to feel at home and that we can be ourselves at work. Finally, a people-at-heart culture means well-being. So, we enjoy the flexibility needed to be and do our best – at work and in life. Zenseact works proactively to create a culture of diversity and inclusion, where individual differences are appreciated and respected. To drive innovation we see diversity as an asset, which means we value and respect differences in gender, race, ethnicity, religion or other belief, disability, sexual orientation or age, etc. Interviews are held continuously, so we highly recommend that you submit your application at your earliest convenience.
Do you want to design and train deep neural networks from scratch? Are you excited about building frameworks for end-to-end learning that make self-driving cars safer? Are you looking for a place to collaborate with experts in your field, in a highly innovative company where you can enjoy genuine work life balance? Do you want to work with the latest technologies like transformers, in a warm inclusive culture - and help save millions of lives in the process? Apply today - no CV needed, all we need is your name, email and phone number! We'll cover the rest later. INSIGHTS FROM THE TEAM At Zenseact, we design and train spatio-temporal neural networks for end-to-end driving — systems that already run in our cars today. Our models are deployed on a single compute platform, processing multi-modal sensor data in real time and making safety-critical decisions on the road. We are a team of engineers and researchers working on the next generation of deep learning for autonomous driving. We work across the full stack: from tailored data pipelines and large-scale training to architecture design, validation and production integration. We train networks from the ground up, using tailored datasets and custom architectures. Collaboration and curiosity drive us forward. Solving these complex problems is a team effort — researchers and engineers learning from each other, sharing knowledge openly, and growing through hands-on challenges in production systems. Our mission is to create models that understand complex environments and make safe decisions in real time. The next major release — including the upcoming EX60 in summer 2026 — will further evolve our AI stack in real-world cars. Here, you combine cutting-edge AI with a culture that values collaboration, flexibility and balance — making space for life outside of work while building technology that truly makes a difference on the road. YOUR MISSION AND DAY-TO-DAY TASKS In this role, you will focus on end-to-end learning approaches for autonomous driving. You’ll design spatio-temporal neural networks, train them on large-scale data, and integrate them into production systems. You’ll collaborate closely with your peers – experts in perception, planning, and software engineering, to share ideas and deliver solutions that matter. Together you’re solving the hardest problems in autonomous driving, training AI to predict the unpredictable. * Develop and optimize deep learning models for end-to-end driving * Build scalable pipelines for data processing and model training * Experiment with architectures such as transformers and recurrent networks * Collaborate across teams to deploy models into real-world scenarios WHAT’S IN IT FOR YOU * Work at the forefront of deep tech in one of the biggest and most interesting, challenging and dynamic AI/ML-companies in Northern Europe. * Collaborate and team-work with highly skilled, innovative, creative and smart people. * Work with people from all over the world, close to what science just came up with – or innovate it yourself. * Enjoy a flexible work approach and a genuinely good work/life balance. QUALIFICATIONS & EXPERIENCE We’re looking for someone who combines technical depth with a sense of responsibility for the bigger picture. You should be analytical, a problem solver, and an active listener who values teamwork and humility. ESSENTIAL EXPERIENCE * Deep knowledge of spatio-temporal neural networks * Strong background in deep learning, software development, and data engineering * Proficiency in Python and frameworks like TensorFlow or PyTorch * Solid understanding of statistics and geometry MERITING EXPERIENCE * Transformers, RNNs, multi-head attention * Perception systems (computer vision, lidar, radar) * Tracking and sensor fusion * Experience with imitation learning or behavior cloning This role may have access to sensitive information, trade secrets, and confidential data. As part of the recruitment process, the selected candidate might undergo a background check. MORE ABOUT ZENSEACT Our software makes a difference. Using AI-based technology to create the ultimate driver support, we’re fighting to end car accidents and make roads safe for everyone. Every year, around 1,4 million people die in traffic while approximately 50 million people get injured. Many get disabled as a result of their injury. We can do better. One purpose, one product. We’re a software company dedicated to revolutionizing car safety. By designing the complete software stack for autonomous driving and advanced driver-assistance systems, we’re fighting to end car accidents and make roads safe for everyone. Zenseact was founded by Volvo Cars, and the teams are based in Gothenburg and Lund, Sweden and Munich in Germany. When we aim for zero accidents faster, we strive to speed up the transition to safe automation. This is essentially achieved by making cars updatable – like a computer or a phone. With regular software updates, a vehicle can be made safer long after its production. By accelerating improvement loops, shortening development cycles, and deploying high-capacity software quickly, we can make cars safer, and faster. Culture with people at heart To achieve our mission of saving lives and ending traffic accidents we must go where nobody has before. It requires us to venture into the unknown, pioneering new technology and pushing the frontier of autonomous driving. While there’s no denying our determination and expertise, we must stand united to succeed. By fostering a culture of support and enablement – a place of psychological safety where all of us can thrive – everything else will follow. We call this a people-at-heart culture. This culture means caring. It means the company cares about me, and we care about one another. It means sharing, so we give each other energy and have fun together. Our culture is also about belonging. It’s important to feel at home and that we can be ourselves at work. Finally, a people-at-heart culture means well-being. So, we enjoy the flexibility needed to be and do our best – at work and in life. Zenseact works proactively to create a culture of diversity and inclusion, where individual differences are appreciated and respected. To drive innovation we see diversity as an asset, which means we value and respect differences in gender, race, ethnicity, religion or other belief, disability, sexual orientation or age, etc. Interviews are held continuously, so we highly recommend that you submit your application at your earliest convenience.
We build the backends behind products that millions of people use every day. Our motto is Shape, Ship, Scale: we work out what to build, ship it, and help it grow. Now, we are looking for a senior backend engineer to join us in Gothenburg. We are six people at Umain in Gothenburg today, and we share an office with around 40 colleagues from across Eidra. So it is a small, close team with a much bigger room behind it. The work You will build and run backend systems for Swedish and international clients. The scale is real: * 400M+ total app downloads * 50M+ monthly active users * Backends handling tens of thousands of requests per second Most of our work is in Kotlin, Go, and TypeScript, and we pick the tool that fits the project rather than forcing one stack onto everything. Day to day that can mean designing cloud-native systems with Terraform across AWS, GCP and Azure, building solid data models, making systems observable with proper metrics, logs and tracing, and owning CI/CD with containerised deployments. You own systems end to end, from API design to operations, and you work closely with product, design, analysis and testing rather than in a silo. What we are looking for You are an experienced backend engineer, roughly five years or more building and running services in production, who is comfortable owning a system from start to finish. You are strong in at least one of Kotlin, Go or TypeScript and happy to pick up the others. You make good technical calls in a team: weighing tradeoffs, reviewing code, mentoring colleagues. And you think past the ticket in front of you to maintainability and long-term health. In consulting the next project rarely looks like the last one. If that sounds like a feature rather than a risk, you will fit in well. Familiarity with agentic development tools is a plus. If you do not tick every box, apply anyway. We care more about how you think and what you can do than about a perfect match on paper. How we work * Equal pay and clear progression. Our career framework sets transparent levels, so pay and growth track what you do, not how well you negotiate. You build your development plan together with your coach. * Everyone gets a coach, for both professional and personal development. * Flexibility that respects your life. Gothenburg is our default office and we work from home when it makes sense. We hire people across different ages and life stages, and we treat family, health and life outside work as normal, not as something to manage around. * Small multidisciplinary teams, genuinely interesting clients, and a real bar for quality. Practical Umain conducts a background check for final candidates in accordance with our internal policies. The check is carried out only with your consent and is ordered by our CISO through our approved screening partner. The scope of the check depends on the role level. This step is performed late in the recruitment process and is used solely to support a secure and fact-based hiring decision. Sound like you? Apply here, or reach out if you want to know more before you do.