Reinforcement Learning Specialist

Tiepoint is a newly established company built on extensive experience and a strong aviation legacy.

Formed from Andøya Space’s unmanned department in partnership with Sundt Air, Tiepoint combines deep expertise in both manned and unmanned operations. The company focuses on surveillance, emergency operations, inspections, mapping, drone support, and AI/data analytics for customers and partners across Norway and internationally.

Tiepoint is positioned for strong growth and operational impact. We use advanced technology to deliver reliable, mission-critical services in demanding environments where safety, precision, and execution matter.

Team members join a high-competence environment where innovation, aviation safety, and operational excellence are central.

Tiepoint is looking for a Reinforcement Learning Specialist to join our team in Stockholm.

This is a full-time, on-site role focused on developing reinforcement learning systems for autonomous drone operations and advanced unmanned systems.

You will design, implement, train, evaluate, and optimise RL algorithms for applications in surveillance, emergency operations, inspections, and autonomous systems. The work will include simulation environments, model training, reward design, policy evaluation, robustness testing, and integration into operational workflows.

This is not a role for maintaining mature models in a settled domain.

You should be ready to take on a challenge that will likely require technologies beyond the current state of the art. Some problems will not have clear answers in existing libraries, papers, or benchmarks. Success will require strong engineering and scientific discipline, creativity, and the ability to translate experimental ideas into robust operational systems.

Our systems are not developed only for controlled indoor tests. Tiepoint conducts regular real-world testing in Northern Norway, where demanding weather, treacherous gusts, and operational constraints are present from the start. The autonomy we build must work in the field.

The role is based in Stockholm, Sweden, with close collaboration across AI, software engineering, aviation, drone operations, and domain experts.

• Design, implement, and improve reinforcement learning algorithms for autonomous drone and unmanned systems applications.
• Build and maintain simulation environments for training, evaluation, and large-scale experimentation.
• Develop reward functions, training pipelines, evaluation metrics, and experiment frameworks.
• Train and evaluate RL models for robustness, safety, scalability, and operational reliability.
• Work on sim-to-real transfer and model validation against real-world flight conditions.
• Collaborate with data engineers, software developers, aviation specialists, and drone operators.
• Integrate RL models into broader AI, autonomy, and full-stack operational systems.
• Analyse large datasets from simulations, tests, and operational environments.
• Document methods, results, limitations, and technical decisions clearly.
• Contribute to Tiepoint’s long-term AI and autonomy strategy.
  

• Strong foundation in reinforcement learning, including practical experience with algorithms such as Q-learning, policy gradients, actor-critic methods, PPO, SAC, DQN, or related approaches.
• Strong programming skills for machine learning, preferably in Python.
• Experience with frameworks such as PyTorch, TensorFlow, JAX, or similar.
• Experience building or working with simulation environments, such as custom simulators, OpenAI Gym-style environments, robotics simulators, or autonomous systems simulators.
• Solid understanding of machine learning fundamentals, including supervised learning, unsupervised learning, model evaluation, optimisation, and generalisation.
• Strong mathematical foundation, including linear algebra, probability, numerical optimisation, statistics, and stochastic processes.
• Ability to design experiments, analyse results, and use data to guide model improvements.
• Experience deploying ML or RL models into production, robotics, embedded systems, or operational software environments.
• Strong software engineering practices, including version control, testing, CI/CD, code review, and maintainable system design.
• Ability to work with multidisciplinary teams and explain complex technical concepts clearly.
• Master’s degree or PhD in Computer Science, Machine Learning, Robotics, Applied Mathematics, Engineering, or a related field, or equivalent practical experience.
• Experience in robotics, autonomous vehicles, drones, aerospace, aviation, or defence-related domains is highly valued.
  

• Experience with sim-to-real transfer, domain randomisation, imitation learning, offline RL, multi-agent RL, or safe RL.
• Experience with control theory, model predictive control, flight dynamics, sensor fusion, or navigation systems.
• Experience with computer vision, perception systems, tracking, or real-time decision-making.
• Experience working with drones, UAV platforms, robotics middleware, embedded systems, or edge AI.
• Experience building tools for large-scale simulation, experiment tracking, model evaluation, and reproducible ML workflows.
• Familiarity with safety-critical systems, aviation constraints, or mission-critical software development.
  

You are technically strong, practical, and comfortable with uncertainty.

You can work from first principles when existing solutions are not enough. You care about models that work outside the lab. You are motivated by real-world autonomy, rigorous experimentation, and systems that must perform under demanding conditions.

You are ready to help build technology that pushes beyond today’s standard approaches.

• A chance to work on applied reinforcement learning for real autonomous systems.
• Direct exposure to operational drone environments and aviation expertise.
• A high-competence team with deep experience in unmanned and manned operations.
• Real technical ownership in a company positioned for strong growth.
• Work on systems where AI, autonomy, software engineering, and field operations meet.
• An on-site role in Stockholm with close collaboration across engineering and operations.
  

We are looking for people who want to build the next generation of autonomous drone systems.

• If you are a reinforcement learning specialist ready for a serious technical challenge, we would like to hear from you.