Harmattan AI · Defence and security
Flight Control & Dynamics Engineer
- Lausanne (On‑site)
- Full-time
Still open on Harmattan AI's site · checked just now
- Education
- A degree
- Posted
What you'll do
As written by Harmattan AI · Read the original
ABOUT THE ROLE
Harmattan AI is pushing the boundaries of high-speed autonomous flight, where control has to hold up at the edge of the envelope. Getting that right across a family of airframes is one of the most demanding parts of the flight software.
As a Flight Control & Dynamics Engineer, working out of Lausanne, Paris, or Zurich, you will own control law design and the system identification that feeds it, setting the control standard as the team grows. You will weigh classical against learning-based methods, from tuned control laws to reinforcement-learning policies trained in simulation and flown on hardware, and decide what actually flies.
RESPONSIBILITIES
System Identification: Design excitation maneuvers and fit airframe models from flight data, with quantified error bounds.
Control Law Design & Tuning: Inner rate and attitude loops through outer position loops, with allocation, gain scheduling, and manual or automated tuning across the airframe family and flight envelope.
Sim-to-Real: Keep the in-house simulator faithful to the identified model, so control developed in simulation transfers to the aircraft.
Model Consumption: Turn the stability derivatives and coefficient tables from Aerodynamics into flying control.
Flight Test & Diagnosis: Verify across simulation, SITL, and HITL, including Monte Carlo campaigns, then fly and iterate from logs.
Mentorship: Depending on seniority, support the team by mentoring junior control and GNC engineers.
Requirements
CANDIDATE REQUIREMENTS
Educational Background: A strong academic record with a degree in aerospace, controls, robotics, or a related STEM field. A practical track record matters more than the specific degree.
System Identification & Control: Proven, hands-on identification and control on multirotor or fixed-wing platforms, validated in flight, with depth in at least one of MPC, INDI, or geometric control.
Embedded Realization: Real-time control implementation on constrained targets, split cleanly between a microcontroller and a companion computer.
Learning-Based Control: Familiarity with reinforcement learning and simulation-based training, and the judgment to know when a learned policy beats a classical design.
Skills
Working languages
English
Company
Last checked . The details above were extracted automatically; the employer's original posting is the authority.
