Autonomy ML Engineer
Build learning-based agents that perceive, decide and fly — in simulation and on real aircraft.
- Level
- L30 — Engineer II
- Location
- Andorra
- Working model
- On-site
- Experience
- ~2–4 years
What this is
SWARM is building the intelligence layer for autonomous drones. We are looking for an Autonomy ML Engineer to build learning-based flying agents that can perceive, decide and act in simulation and, ultimately, on real aircraft.
A core objective is to beat the state of the art on SWARM's autonomous-flight benchmarks, including SOTApilot, and transfer those capabilities into commercial autonomous-drone systems such as autonomous inspection and surveillance.
This is not a generic AI, LLM or prompt-engineering role.
What you will work on
- Train autonomous flight policies for navigation, obstacle avoidance and mission execution.
- Improve benchmark performance across unseen environments, not just known training scenarios.
- Design observations, actions, rewards, curricula and evaluation strategies.
- Run simulation experiments, analyze failures and iterate systematically.
- Improve robustness, safety, speed and generalization of learned policies.
- Develop capabilities for more complex missions: search & rescue, interception and multi-agent coordination.
- Combine learning-based autonomy with classical planning and control where appropriate.
- Help move successful policies from simulation onto real drones.
- Contribute perception and autonomous decision-making capabilities required by commercial projects.
- Documenting SWARM's architecture, inventions, and engineering systems.
What we're looking for
Approximately 2–4 years, ideally around 3, in a highly relevant professional or research environment. We care more about what you have built than the number of years on your CV.
Someone who has already trained autonomous or reinforcement-learning systems that actually work, and can independently improve them through structured experimentation.
An unconventional background with strong demonstrated work counts for more here than a conventional one without it.
What matters
The left column is what the work leans on. The right column is what makes an application stand out.
Core to the role
- Strong Python and PyTorch
- Reinforcement learning and continuous control
- PPO, SAC, TD3 or related methods
- Robotics / physics simulation
- Reward design, evaluation and failure analysis
- Structured experimentation and reproducibility
- Robotics fundamentals: position, velocity, orientation, coordinate frames
- Ability to own open-ended technical problems independently
Valuable, not required
- Isaac Sim / Isaac Lab, MuJoCo, PyBullet, Gazebo or similar
- Computer vision, depth or learned perception
- Curriculum learning and domain randomization
- Sim-to-real transfer
- Multi-agent reinforcement learning
- Motion planning and control
- ROS2, PX4 / MAVLink
- ONNX / TensorRT / edge deployment
- C++
What L30 means here
An independent engineer. You are not expected to define SWARM's whole architecture — you are expected not to need step-by-step instructions.
- 01
Understand why the current system fails.
- 02
Propose experiments and technical approaches.
- 03
Implement and train them.
- 04
Evaluate results rigorously.
- 05
Iterate until performance measurably improves.
What success looks like
Success in this role is measurable.
Build increasingly capable flying agents.
- Higher autonomous-flight benchmark performance.
- Better generalization across unseen environments.
- Fewer collisions, failures and unsafe behaviors.
- Faster and more reliable mission completion.
- Successful progress from simulation toward real flight.
- New autonomous capabilities deployed in customer projects.
A clear career path
- Promotions follow demonstrated scope, independence and impact — not years served.
- Everyone knows their level and what the next one expects.
- Engineers keep progressing technically without having to become managers.
- L10Associate Engineer
- L20Engineer I
- L30Engineer IIhiring here
- L40Engineer III
- L50Senior Engineer
- L60Staff Engineer
- L70Senior Staff Engineer
- L80Principal Engineer
- L90Distinguished Engineer
L10
Associate Engineer
L20
Engineer I
L30
Engineer II
L40
Engineer III
L50
Senior Engineer
L60
Staff Engineer
L70
Senior Staff Engineer
L80
Principal Engineer
L90
Distinguished Engineer
Benefits and support
Competitive net compensation based on level, relevant experience and specialist expertise.
Early-joiner equity
Equity participation as one of SWARM's early employees.
Competitive net salary
Competitive net compensation based on level, relevant experience and specialist expertise.
22 days paid vacation
22 working days of paid vacation per year.
Remote Fridays
Two remote-work Fridays per month. The role is otherwise on-site in Andorra.
Relocation support
Relocation and administrative support for candidates moving to Andorra.
Clear career progression
A transparent career path with regular progression and compensation reviews.
Professional development
Support for relevant courses, conferences and certifications on a case-by-case basis.
Compute without barriers
Generous access to compute, AI tokens and development resources, with minimal internal bureaucracy.
Want to build flying agents?
If autonomous systems, reinforcement learning and real-world robotics are the problems you want to spend your time on, we'd like to hear from you.
A cover letter is optional. What we read first is what you built and how you knew it worked.
