Embedded AI & Vision Systems Intern

Location: Los Angeles, CA or Louisville, KY

Duration: 10–16 weeks

About the work

Prototype, benchmark and document edge AI vision workflows using the AMD Kria KV260 Vision AI Starter Kit. Focus on running models on embedded hardware, checking vendor instructions against observed behavior and producing reproducible engineering results.

What you will do

• Set up the KV260 development kit, software environment and camera interfaces; document dependencies and recovery steps.
• Deploy and benchmark object-detection, segmentation or tracking models on live video.
• Measure latency, throughput, power where instrumented, and stability under a documented test configuration.
• Maintain code, build scripts and setup guides in Git/GitHub, subject to the team’s disclosure and repository-access decisions.
• Identify discrepancies between vendor documentation and actual system behavior, then create clear troubleshooting notes and reproducible examples.
• Record model, toolchain, firmware and dataset versions so results can be repeated.
• Present results in a final technical report and demonstration, including known limitations and a comparison with an agreed baseline.

What you bring

• Pursuing a BS/MS in electrical engineering, computer science, robotics or a related field.
• Linux, Python/C++ and Git/GitHub experience.
• Basic machine-learning and computer-vision knowledge.

Useful additional experience

FPGA or hardware acceleration experience with Vitis, Vitis AI or similar tools; edge AI work on Jetson, Coral, FPGA or related platforms.

Initial project to agree

For the agreed 10–16-week project, prepare a reproducible KV260 setup, one benchmarked vision workflow and a final technical report/demo. Set intermediate checkpoints for bring-up, baseline measurements and repeatability; public portfolio material depends on approved disclosure.

About AstraQua

AstraQua is developing a modular autonomy architecture with AQFM as its shared intelligence foundation. Specialized agents contribute perception, reasoning, health and coordination. AstraSense is the health-intelligence agent, with electrified aviation as an initial research application; it connects condition and remaining capability with mission decisions. Our approach to safe AI emphasizes defined operating boundaries, deterministic safety controls, operator authority and behavior designed for verification and validation.

How to apply

Email your resume, job title and preferred location (Los Angeles, CA or Louisville, KY) to careers@astraqua.com.