Senior Data Scientist (Integrity)
Core
Develop advanced Computer Vision and Multimodal LLMs for precise OCR, KYC verification, and document/image information extraction to support user onboarding and identity verification workflows.
Role type
Senior IC Computer Vision and Multimodal LLM Data Scientist
Builds
Production ML models for document processing pipelines (OCR, Vision LLMs) and identity verification systems
Domain
Fraud, risk, digital identity, and safety in the fintech/superapp industry
Deliverable
production ML models
Required skills
Python, Spark, SQL, TensorFlow, PyTorch, Computer Vision, Multimodal LLMs, OCR, document information extraction, model fine-tuning, end-to-end pipeline architecture, production deployment, model monitoring, latency optimization
Preferred skills
Experience translating academic research into product impact, explaining technical concepts to non-technical stakeholders
Technologies
Python, Spark, SQL, TensorFlow, PyTorch, git, git-flow
Responsibilities
Design, train, and fine-tune state-of-the-art OCR and Vision LLM models; Architect and own end-to-end document processing pipelines from concept to production; Deploy models into high-throughput environments and implement monitoring for performance and latency; Research and prototype latest AI advancements; Explain model trade-offs and findings to stakeholders
Seniority
Senior, hands-on IC