Senior Staff Software Engineer, Perception

WHO WE ARE AeroVect is transforming ground handling with autonomy, redefining how airlines and ground service providers around the globe run day-to-day operations. We are a Series A company backed by top-tier venture capital investors in aviation and autonomous driving. Our customers include some of the world’s largest airlines and ground handling providers. For more information, visit www.aerovect.com http://www.aerovect.com. YOU WILL - Architect 3D object detection models, including multi-modal approaches (camera, LiDAR, Radar).

• Build and maintain data collection and evaluation (metrics) pipeline.
• Develop a proprietary multi-modal dataset for training and evaluation.
• Train, deploy and monitor 2D/3D object detection models to production.
• Build and execute a roadmap for the perception system - Mentor junior engineers about best practices.

• 7+ years of focused experience in architecting and deploying 2D/3D object detection models.
• Worked on entire perception stack (sensing, preprocessing, detection & tracking) - Python proficiency - The ability to identify gaps and lead cross functional projects WE PREFER - PhD in Computer Science, Robotics, or a related discipline - Full stack AV knowledge - Experience in architecting perception systems (detection & tracking) - Publications in major conferences like CVPR, ICRA, NeurIPS, IJCAI, AAAI etc

• Build a concise portfolio that includes at least one end‑to‑end multi‑modal perception project (e.g., camera + LiDAR sensor fusion for 3D object detection). Host the code on GitHub, document the data pipeline, model architecture (PyTorch/TensorFlow), training curves, and real‑time inference benchmarks on an edge GPU; include a short video demo showing detection on a realistic airport ground‑handling scenario.
• In your resume and cover letter, highlight concrete achievements with the exact tools AeroVect uses: e.g., “Designed and deployed a TensorRT‑optimized 3D detector on NVIDIA Jetson AGX Xavier, reducing latency from 120 ms to 38 ms while maintaining 0.92 mAP on a custom radar‑augmented dataset.” Mention experience with ROS 2, Docker/Kubernetes for CI/CD, and cloud storage (AWS S3, GCS) for large sensor datasets.
• Prepare for system‑design interviews by mapping out the full perception stack: data ingestion (high‑bandwidth LiDAR/Radar streams), preprocessing, multi‑modal fusion, model serving, and monitoring. Sketch how you would implement a scalable evaluation pipeline (e.g., using Apache Beam or Airflow) that logs per‑frame metrics and triggers automated retraining alerts.
• Demonstrate remote‑team readiness: list the collaboration platforms you’ve mastered (GitHub Projects, Notion, Slack, Zoom, Miro) and give a brief example of how you coordinated a cross‑functional effort (software, hardware, data science) across time zones to ship a perception update within a sprint.
• When negotiating compensation, research recent Series A funded AI‑perception startups (average total cash + equity for senior staff engineers ranges $250k–$320k base plus 0.1–0.3 % equity). Cite AeroVect’s runway and growth milestones, and be ready to ask for a remote‑work stipend (home office, high‑speed internet) and a clear equity vesting schedule aligned with product milestones.