Senior Applied Computer Vision Engineer
Fully remote position for professionals residing in Europe.Full-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonMachine LearningPyTorchComputer Vision
Requirements
- Extensive experience building, deploying, and improving production-grade computer vision systems.
- Strong proficiency in Python and modern deep learning frameworks such as PyTorch.
- Hands-on expertise in video-based computer vision, including object detection, multi-object tracking, event recognition, identity association, or video analytics.
- Solid understanding of geometric computer vision concepts including camera calibration, homography estimation, projective geometry, and mapping image coordinates to real-world environments.
- Experience improving tracking systems in challenging scenarios involving occlusions, noisy detections, identity preservation, and object interactions.
- Demonstrated ability to evaluate model performance, identify weaknesses, and implement effective optimization strategies.
- Experience adapting models to diverse real-world environments using techniques such as transfer learning, domain adaptation, data augmentation, and fine-tuning.
- Strong software engineering practices with the ability to write clean, maintainable, production-quality code.
- Ability to work independently, prioritize multiple initiatives, and drive projects through completion.
- Excellent communication and collaboration skills within cross-functional and client-facing environments.
Responsibilities
- Develop, enhance, and maintain production-ready computer vision models for sports video analytics, including player and ball detection, tracking, event recognition, and identity association.
- Design and improve geometric computer vision solutions such as camera calibration, homography estimation, field registration, and coordinate mapping.
- Evaluate existing computer vision pipelines, identify performance bottlenecks, analyze failure modes, and implement practical improvements to increase accuracy, scalability, and robustness.
- Adapt machine learning models and vision pipelines to support new sports, leagues, stadiums, camera configurations, and varying video quality conditions.
- Design and execute experiments covering dataset creation, augmentation, model training, fine-tuning, evaluation, and production readiness.
- Collaborate with data, software, platform, and DevOps teams to deploy scalable machine learning solutions into production environments while improving inference performance, monitoring, and operational reliability.
- Define evaluation metrics, testing strategies, and quality assurance processes to ensure consistent model performance over time.
- Lead technical initiatives from early research and prototyping through deployment, communicating technical decisions and trade-offs effectively across engineering and stakeholder teams.
View Full Description & ApplyYou'll be redirected to the employer's site
