Principal Perception Architect

Caterpillar Caterpillar · Industrial · Irving, TX

Principal Perception Architect / Team Lead responsible for defining and leading the end-to-end perception architecture for advanced autonomous machine systems at Caterpillar. This role involves shaping how machines sense, understand, and act on their environment, integrating various sensors and ML models, and ensuring the perception system supports real-time machine behavior, edge deployment, and safety. The position requires strong systems thinking, architectural tradeoff analysis, and leadership of a perception architecture team.

What you'd actually do

  1. Define and own the end-to-end perception architecture for autonomous machine systems, including sensor integration, sensor fusion, perception ML, scene understanding, world model inputs, data flow, validation, and safety analysis.
  2. Lead the Perception Architecture Team by setting technical direction, aligning architecture priorities, guiding key design decisions, and ensuring the team works as one cohesive architecture function.
  3. Create the perception technical roadmap that connects near-term product needs with long-term autonomy capability, scalability, reliability, and platform reuse.
  4. Drive architecture decisions and tradeoffs across perception accuracy, latency, compute usage, sensor coverage, cost, power, robustness, safety, and deployability on edge platforms.
  5. Ensure perception architecture supports real-world operating conditions, including sensor degradation, harsh environments, blind spots, poor visibility, machine vibra

Skills

Required

  • Perception architecture definition and ownership
  • Sensor integration and fusion
  • Machine learning for perception
  • Scene understanding
  • World model inputs
  • Perception data flow management
  • Validation and safety analysis for perception systems
  • Systems thinking
  • Autonomous machine systems
  • Edge deployment
  • Real-time machine behavior support
  • Technical roadmap creation
  • Architecture tradeoff analysis (accuracy, latency, compute, cost, safety, etc.)
  • Team leadership and guidance

Nice to have

  • Experience with cameras, lidar, radar, stereo, ultrasonic, GNSS sensors
  • Familiarity with planning, control, and machine behavior logic
  • Experience with simulation systems
  • Understanding of robotics autonomy logic

What the JD emphasized

  • end-to-end perception architecture
  • perception architecture
  • perception ML
  • perception data flow
  • perception outputs
  • perception and downstream consumers
  • perception capabilities
  • perception accuracy
  • perception system architecture
  • perception data and simulation
  • perception validation and safety analysis
  • perception outputs are useful for planning
  • perception outputs are deployable
  • perception architecture supports real-world operating conditions

Other signals

  • Define and lead the end-to-end perception architecture for advanced autonomous machine systems.
  • shaping how machines sense, understand, represent, validate, and act on the external world
  • connect perception technology with actual machine autonomy needs
  • define clear technical contracts between perception and downstream consumers