Senior Autonomy Controls Engineer Learning-Based Control
Teleo, a Havoc company, provides supervised-autonomy technology that retrofits heavy equipment for remote and semi-autonomous operation.
Funding history
About Teleo
Teleo supplies a full-stack system—retrofit hardware, mesh connectivity, remote command center, and the Teleo Insite analytics platform—for fleet-scale supervision of heavy machinery in construction, mining, logistics, and related industries.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will transition vehicle control from manually tuned MPC to learning-driven policies. You will collect and analyze real-world data, identify plant models, implement learning-based control, integrate controllers safely, define control interfaces, and validate policies before deployment on vehicles.
Requirements
- 2-3 years of experimental data collection and data-analysis experience for automatic-control plant models
- Production-quality software engineering skills in C, C++, or Python
- Deep understanding of modern robotics control systems
- Experience with learning-based control or policy optimization for real-world systems
- Ability to work near hardware and real-time constraints
Responsibilities
- Generate test plans and collect real-world data for plant-model system identification
- Use real-world data to estimate parameters for automatic-control plant models
- Design and implement learning-based control approaches
- Reduce reliance on hand-tuned control parameters using data-driven methods
- Integrate learned controllers into the vehicle-control stack safely and incrementally
- Define interfaces between MPC, PID, state estimation, and learning-based components
- Translate classical-control insights into learning-friendly formulations
- Establish validation criteria for learned control policies before real-vehicle deployment