Senior Computer Vision and Deep Learning Engineer
New
S
Svitla Systems Inc.Computer vision
Full-time position (40 hours per week) in Europe; Locations: Kraków, Warszawa, Gdańsk, Katowice, Poznań, Wrocław, Sofia, Budapest, BucharestFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonNumpyOpenCVPyTorch
Requirements
- Demonstrate strong programming skills in Python and experience with NumPy and OpenCV.
- Have hands-on experience training and deploying deep learning models in PyTorch.
- Bring a solid background in scene text and document understanding, including text detection, text recognition, sequence decoding, confidence calibration, constrained decoding, and reading-order and layout grouping.
- Have practical multi-view geometry experience, including local feature detection, description and matching, homography estimation, RANSAC and its variants, inlier analysis, and perspective warping.
- Be able to debug chained coordinate-space transforms and polygon geometry.
- Apply systematic failure analysis, including error taxonomies, reproducible test cases, quantified failure buckets, and controlled ablations.
- Have experience with dataset construction and curation, augmentation, synthetic and degraded data generation, domain adaptation, fine-tuning, and hyperparameter sweeps.
- Benchmark rigorously before and after changes against tracked baselines.
- Be proficient with Hydra for configuration management and Weights & Biases for experiment tracking.
- Have experience working on remote GPU servers and clusters and in containerized environments.
- Have experience with Git and GitHub for version control and a habit of testing numerical and geometric code.
- Collaborate effectively on teams and shared codebases, including remote projects, and write clear technical analysis reports.
Responsibilities
- Own and improve the OCR pipeline end to end.
- Diagnose failures on real customer images and identify root causes.
- Develop and optimize text detection, recognition, decoding, and layout components.
- Work with image geometry, feature matching, homographies, RANSAC, and perspective transforms.
- Build and curate datasets, run augmentations and fine-tuning, and conduct controlled experiments.
- Benchmark changes against tracked baselines and document measurable improvements.
- Use PyTorch, OpenCV, NumPy, Hydra, Weights & Biases, GPUs, containers, and Git.
- Collaborate with the team on shared codebases and provide clear technical analysis.
View Full Description & ApplyYou'll be redirected to the employer's site
