Engineering Manager, Computer Vision

Flock is a leading safety technology platform focused on proactive crime prevention and security. The Engineering Manager for Computer Vision will lead a team of engineers to advance Flock’s license plate recognition and vehicle intelligence models, ensuring systems perform reliably at scale while fostering a culture of technical excellence and continuous learning.

Responsibilities:

• Lead and grow a high-performing ML Vision team while remaining hands-on in the design, development, and optimization of Flock’s license plate recognition and vehicle intelligence models
• Architect and guide improvements in model accuracy, robustness, and generalization across diverse real-world conditions, hardware variations, and edge cases
• Drive innovation in vehicle and license plate modeling, extending capabilities to support new data sources and evolving product needs
• Oversee and actively participate in the full ML lifecycle — data strategy, training pipelines, validation, deployment, monitoring, and retraining — ensuring scalable, reliable production systems
• Balance forward-looking innovation with maintenance and operational excellence, proactively addressing model drift, technical debt, and system reliability
• Partner cross-functionally with product, hardware, and platform teams to translate business priorities into a clear technical roadmap and deliver high-impact vehicle intelligence capabilities
• Mentor and develop engineers through technical leadership, code reviews, architectural guidance, and structured feedback, fostering a culture of ownership and continuous improvement
• Drive continuous improvement in the team's engineering and ML development processes, actively removing roadblocks to enable faster innovation and execution

Requirements:

• 7+ years of industry experience in Machine Learning, with deep expertise in computer vision and deploying models in real-world production systems
• Experience leading engineers through formal management or strong technical mentorship, with a track record of growing individuals and elevating team performance
• Strong hands-on proficiency in PyTorch and modern deep learning workflows, including model training, fine-tuning, evaluation, and failure analysis
• Demonstrated ownership of ML initiatives end-to-end — from data strategy and experimentation to deployment, monitoring, and iterative improvement in production
• Experience improving model robustness and generalization across diverse environmental conditions, hardware variability, and operational edge cases
• Solid engineering fundamentals in Python, with experience building reliable, maintainable systems and contributing to shared infrastructure
• Comfortable balancing hands-on technical contributions with roadmap alignment, cross-functional collaboration, and team development in a fast-moving environment
• Experience building or deploying computer vision systems for real-world edge environments (e.g., traffic cameras, embedded systems, mobile or drone imagery)
• Familiarity with large-scale model retraining workflows, model drift detection, and continuous evaluation in production ML systems
• Experience improving inference efficiency through model compression techniques (e.g., distillation, quantization, pruning) or hardware-aware optimization
• Exposure to multi-GPU or distributed training workflows for scaling training of large vision models
• Experience leading technical roadmap planning or scaling teams through periods of rapid product growth