Company Overview
At Skild AI, we are building the world's first general purpose robotic intelligence that is robust and adapts to unseen scenarios without failing. We believe massive scale through data-driven machine learning is the key to unlocking these capabilities for the widespread deployment of robots within society. Our team consists of individuals with varying levels of experience and backgrounds, from new graduates to domain experts. Relevant industry experience is important, but ultimately less so than your demonstrated abilities and attitude. We are looking for passionate individuals who are eager to explore uncharted waters and contribute to our innovative projects.
Position Overview
We are seeking an experienced Camera Systems Software Engineer to own camera integration and enablement for real-time robotic systems built on NVIDIA Tegra platforms. This person will be responsible for the full camera lifecycle, from defining requirements with external camera partners to integrating, debugging, and maintaining low-latency camera pipelines using the Tegra camera stack.
This is a highly hands-on systems role that sits at the intersection of Linux, camera hardware, real-time software, calibration, synchronization, and high-level software interfaces. The ideal candidate has deep experience bringing up camera sensors, debugging low-level hardware/software issues, working with camera vendors, and building reliable APIs that expose synchronized camera data to perception, robotics, and autonomy systems.
Responsibilities
- Own camera systems end to end, including vendor requirements, sensor/module selection, hardware bring-up, software integration, debugging, calibration, validation, and long-term maintainability.
- Work directly with camera vendors and hardware partners to define requirements for custom cameras, including sensors, optics, frame rates, exposure behavior, synchronization, timestamping, calibration needs, mechanical constraints, thermal constraints, and image-quality targets.
- Develop and maintain low-level camera software, including sensor configuration, camera drivers, device-tree changes, capture-path validation, timestamp handling, metadata handling, and camera control interfaces.
- Debug camera issues across the hardware/software boundary, including MIPI CSI-2, GMSL or FPD-Link, I2C control, power/reset/clock sequencing, dropped frames, timestamp instability, bandwidth limits, corrupted images, ISP behavior, and sensor-mode configuration.
- Design reliable, low-latency camera pipelines for real-time robotic systems, with careful attention to buffering, memory movement, CPU/GPU interaction, scheduling, throughput, timing jitter, and dropped-frame behavior.
- Build clean high-level APIs that expose camera frames, timestamps, metadata, calibration parameters, diagnostics, and health/status information to perception, autonomy, logging, and product software.
- Collaborate closely with perception, robotics, embedded systems, electrical engineering, and external hardware partners to ensure the camera stack is reliable, observable, and production-ready.
Preferred Qualifications
- Bachelor’s or Master’s degree in Computer Engineering, Electrical Engineering, Robotics, Computer Science, or a related technical field.
- 5+ years of hands-on experience with embedded camera systems, including sensor bring-up, camera module integration, driver-level debugging, and board-level validation.
- Strong proficiency in C/C++ for Linux or performance-sensitive systems, including multithreading, memory management, profiling, and low-latency software design.
- Experience with camera interfaces and supporting hardware, such as MIPI CSI-2, I2C, GMSL, FPD-Link, serializers/deserializers, power sequencing, reset sequencing, clocks, and sensor mode tables.
- Experience developing or modifying Linux camera drivers, device trees, V4L2 drivers, media controller graphs, or similar low-level camera integration components
- Strong understanding of vision requirements for real-time systems, including timestamping, synchronization, buffering, scheduling, latency measurement, jitter reduction, dropped-frame analysis, and deterministic data delivery.
- Experience with multi-camera synchronization, hardware triggering, PTP, PPS, camera-IMU synchronization, or other precise timing systems.
- Working knowledge of image sensors and imaging pipelines, including Bayer formats, RAW capture, YUV/RGB formats, HDR modes, exposure/gain control, white balance, ISP behavior, and image-quality tradeoffs.
- Proficient with debugging tools and workflows, including kernel logs, tracing, profiling, oscilloscopes or logic analyzers, long-duration test scripts, capture validation tools, and reproducible failure isolation.