Sensor Technology Fellowship (6-12 months)

Sensor Technology Fellowship (6-12 Months)

We are looking for a motivated intern to join our Autonomous Driving Sensor team. You will support the evaluation and benchmarking of perception sensors — primarily LiDAR, radar, and camera — used in autonomous driving applications. This is a hands-on engineering role where you will work directly with sensor hardware, recorded datasets, and processing pipelines to characterize sensor performance under real-world conditions.

Possible tasks within this role include:

• Conduct systematic sensor assessments covering detection range, resolution, field of view, and accuracy across environmental conditions (weather, lighting, temperature)
• Process and analyze 3D point cloud data from LiDAR and radar sensors to extract performance metrics such as point density at range, reflectivity response, and angular resolution
• Define and compute sensor KPIs; integrate new KPIs in assessment pipeline
• Develop and maintain Python-based tooling for automated sensor data evaluation and reporting
• Translate sensor-level measurement results into system-level context: map component performance (e.g., detection range, angular accuracy) to Self-Driving System (SDS) requirements and identify gaps or margins
• Support test campaign planning, including scenario definition, and environmental condition coverage
• Document results in structured test reports and contribute to sensor selection decisions
• Leverage modern AI tools (Claude, Codex, MCP integrations) to accelerate data analysis, code development, and documentation — and help the team adopt AI-native workflows

What you'll learn:

• Systems engineering thinking: how to trace sensor-level performance (component KPIs) to full Self-Driving System requirements — understanding where a sensor's capabilities enable or limit system-level safety and functionality
• State-of-the-art sensor hardware: hands-on experience with current-generation LiDAR, radar, and camera sensors — from unboxing and integration to data capture and analysis
• Test case development: how to derive targeted test cases from system requirements, identify coverage gaps, and design experiments that produce actionable engineering evidence
• Effective engineering communication: presenting technical findings clearly to cross-functional stakeholders, writing concise test reports, and supporting decision-making in a fast-moving team
• AI-native engineering workflows: building proficiency with LLM tools and agentic integrations to accelerate analysis, automate repetitive tasks, and establish best practices the team can scale
• Sensor physics in practice: how datasheet specifications translate (or fail to translate) to real-world performance under adverse conditions

Qualification requirements:

• Required education: currently pursuing a degree (Bachelor's or Master's) in Electrical Engineering, Computer Science, Physics, Robotics, or a related technical field. If you are pursuing a Bachelor's degree, you must have senior standing at a minimum. You must have a 3.0 GPA (transcripts are required for consideration)
• Required skills: familiarity with Python for data analysis and scripting (NumPy, pandas, matplotlib or similar); familiarity with Ubuntu; background with Ethernet and serial communication; basic knowledge of C++ (reading and modifying existing codebases); foundational understanding of at least one sensor modality (LiDAR, radar, or camera) — operating principles, key parameters, and typical limitations; ability to work with 3D point cloud data (coordinate systems, transformations, filtering); strong analytical mindset and attention to detail when interpreting measurement data; hands-on experience with LLM-assisted workflows (e.g., Claude, ChatGPT, GitHub Copilot/Codex) for coding, analysis, or technical writing — you actively use AI tools to work faster and smarter
• Nice to have: experience with point cloud libraries (Open3D, PCL, or similar); familiarity with sensor data formats (PCD, rosbag, MF4, PCAP); exposure to radar signal processing concepts (Doppler, CFAR detection, range-velocity ambiguity); knowledge of image processing fundamentals (ISP pipeline, lens distortion, HDR); understanding of sensor fusion concepts and coordinate frame calibration; experience with Git, Linux, and automated testing workflows; familiarity with MCP (Model Context Protocol) or building custom AI tool integrations

Compensation data: for a Silicon Valley fellowship, the hourly rates are as follows: Bachelor's: $34/hr, Masters: $38/hr, PhD: $42/hr

MOIA America is an equal opportunity employer. We welcome and encourage applicants from all backgrounds, and do not discriminate based on race, sex, age, disability, sexual orientation, national origin, religion, color, gender identity/expression, marital status, veteran status, or any other characteristics protected by applicable laws.