machine learning engineer

Sumsub is a leading full-cycle verification platform that enables scalable compliance. The platform provides identity and business verification, ongoing monitoring, and customizable analytics with a no-code interface to help clients prevent fraud and maintain global compliance.

• Own the full ML lifecycle from data gathering and training to optimization, production rollout, and continuous quality assessment;
• Train SOTA CV/ML models to detect deepfakes, segment documents, and uncover complex anomaly patterns in real-time;
• Balance research and speed by choosing between sophisticated deep learning models and clever heuristics;
• Serve models efficiently using FastAPI and PyTorch to ensure integration with high-load Java backends;
• Build and monitor ML pipelines and dashboards using Airflow, ClickHouse, and Superset.

• 4+ Years of experience as an ML / CV Engineer in fast-paced, high-load product environments;
• Strong background in Deep Learning frameworks, specifically PyTorch;
• Solid production-grade engineering skills;
• Up-to-date knowledge of SOTA and practical baselines in image segmentation, text extraction, or anomaly detection;
• Autonomous product ownership skills;
• Proactive communication skills for alignment with PMs and backend teams;
• Nice to have: Experience with big data and stream processing tools (Kafka, Flink, Trino, or ClickHouse), hands-on experience with Generative AI (GANs, Diffusion models) or adversarial attack simulation, background in the fintech, anti-fraud, or KYC/KYB domain.

• Fair and transparent pay benchmarked to the market;
• Remote-first, trust-based culture with flexible working hours;
• Extra time off including birthday holiday, 10 personal days, 7 sick days, and additional time for Christmas and New Year;
• Learning opportunities and coverage for role-specific events;
• Fully covered team offsites;
• Provision of necessary tools and hardware.