Data Scientist II (Computer Vision)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Data Scientist II (Computer Vision): Building and improving machine learning models for document verification with an accent on document classification, image quality assessment, and fraud detection. Focus on implementing deep learning architectures, owning end-to-end ML pipelines, and optimizing model performance for production.
Location: Remote (US). Note: Employer cannot provide support for H1, F1, or OPT visas
Salary: $140K – $170K
Company
is building the identity trust infrastructure for the digital economy to verify identities and stop fraud in real time.
What you will do
- Develop and maintain ML models for document classification, field extraction, and fraud detection.
- Implement and evaluate deep learning architectures, including CNNs and transformer-based models.
- Own end-to-end ML pipelines from data preparation to production deployment.
- Perform error analysis and model diagnostics to propose data-driven improvements.
- Collaborate with engineering and product teams to ensure reliability and performance.
- Write maintainable production-quality code and contribute to shared ML tooling.
Requirements
- Bachelor’s degree in Computer Science, Engineering, Data Science, or a related field.
- 5 years of professional experience in machine learning or data science.
- Proficiency in Python and ML frameworks like PyTorch or TensorFlow.
- Experience applying CNNs and transformer-based models in real-world computer vision systems.
- Strong understanding of ML fundamentals, including regularization and transfer learning.
- Must have valid US work authorization (no H1, F1, or OPT support provided).
Culture & Benefits
- Competitive salary with equity and bonus offers.
- High-responsibility environment with a high technical bar.
- Opportunity to solve complex, high-impact problems in the identity trust domain.
- Remote work setup within the US.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →