Senior Engineer, Research-to-Product Perception (R6022)

Location: San Diego, California, United States; Workplace: On-site

Company

Develops autonomous systems, including aircraft and vehicles, powered by the Hivemind autonomy product.

What you will do

• Evaluate emerging multimodal computer vision, visual foundation model, and embodied AI methods against representative sensor data and autonomy requirements.
• Build prototypes and experiments to identify model strengths, limitations, failure modes, and deployment opportunities.
• Combine learned and classical approaches to improve detection, tracking, geometric vision, and sensor fusion.
• Optimize and integrate perception capabilities for edge deployment using Python and C++.
• Deliver tested and documented capabilities and support adoption by other engineering teams.

Requirements

• PhD in computer vision, machine learning, robotics, or a related field, or equivalent advanced research and hands-on engineering experience.
• Research depth in multimodal vision, visual foundation models, video understanding, open-vocabulary perception, or embodied learning.
• Strong Python skills and experience with PyTorch or a comparable machine learning framework.
• Experience designing experiments, evaluating data, and analyzing model failures.
• Experience building substantial research software and an interest in developing production-quality C++.
• Collaborative approach to solving complex perception and autonomy problems.

Nice to have

• Experience bringing research prototypes into sustained production use.
• Experience with robotics, real sensors, temporal data, or multi-sensor perception.
• Familiarity with vision-language models, vision-language-action models, or embodied AI.
• Experience with C++, edge inference, or model optimization using ONNX, TensorRT, or CUDA.