Kodama Systems is a technology company transforming the forestry industry with teleoperation and supervised autonomy. They are seeking a senior or principal engineer who can translate emerging capabilities in computer vision and machine learning into reliable vehicle systems.
Responsibilities:
- Design, implement, and maintain production C++ software for NVIDIA Jetson platforms, cloud services, and peripheral devices
- Lead sensor integration efforts including camera pipelines, synchronization, calibration, and performance validation
- Debug complex distributed systems involving timing, bandwidth required vs reliability, and hardware faults
- Guide performance optimization across CPU, GPU, and memory on constrained edge platforms
- Shape how computer vision and ML models are deployed, versioned, monitored, and updated on embedded systems
- Ensure perception systems are designed for operational realities including startup behavior, degraded modes, logging, and field diagnostics
- Define data capture, labeling, and offload strategies that support continuous improvement without compromising system stability
- Partner with autonomy the team to align model capabilities with platform constraints
- Own the end-to-end architecture of perception pipelines and data offload
- Balancing near-term delivery and field reliability
- Set technical standards for observability, fault detection, recovery, and safe-state behavior
- Ensure systems are testable across simulation, hardware-in-the-loop, and deployed vehicles
- Lead root-cause analysis of field incidents and drive systemic fixes rather than local patches
- Incorporate safety-critical thinking and redundancy where appropriate without unnecessary complexity
- Own the evolution of build, deployment, and provisioning systems spanning C++, Python, Rust, and firmware
- Ensure reproducibility, traceability, and rollback capability across all deployed systems
- Act as a technical authority and mentor across robotics, embedded, and autonomy teams
- Identify architectural risks early and proactively align stakeholders on mitigation strategies
- Raise the engineering bar through design reviews, technical documentation, and shared standards
Requirements:
- 10+ years of experience delivering complex software-driven systems, with significant time in robotics, autonomy, or embedded products
- Deep expertise in C++/Python and systems-level programming
- Familiarity with GPU-accelerated pipelines
- Hands-on work with TensorRT, CUDA, OpenCV, or GPU-accelerated inference pipelines
- Proven track record deploying computer vision or ML systems on real hardware under operational constraints
- Strong understanding of hardware–software integration including sensors, buses, timing, and failure modes
- Experience designing systems that are observable, debuggable, and resilient in the field
- Extensive experience with embedded Linux and edge computing platforms such as NVIDIA Jetson
- Deep experience with ROS 2 or other robotics middleware at scale
- Experience with safety-critical, industrial, or regulated systems
- Experience with Prometheus, Grafana, or similar observability tooling
- Experience designing data pipelines that support ML iteration and fleet learning
- Prior responsibility for multi-year platform architecture decisions
- Experience operating robotic systems in harsh, remote, or safety-sensitive environments