Fintech Algorithm Lead

DiDi Labs • San Jose, CA

2h

About The Position

You will own a frontier algorithm topic and take it from research all the way to production — design, train, evaluate, deploy — and be accountable for its online performance. We don't give you a task list; we give you a sufficiently large problem and a rare dataset in the industry: multi-domain behavioral data across payment, mobility, food delivery, and credit, for the same cohort of users, spanning the full temporal scale from millisecond-level event tracking to daily / weekly-level transactions. The methodology is yours to define; we only care about how far you can push this problem.

Requirements

• Deep expertise in at least one of the key directions: Financial Behavior Sequence Foundation Model, Representation Learning and Self-Supervised Learning, or Identity Recognition and Biometric Verification.
• Ability to take a topic from research to production.
• Experience in designing, training, evaluating, and deploying algorithms.
• Accountability for online performance.
• Ability to define methodologies and solve complex problems.
• Willingness to go deep in one direction and become an owner.
• Skill in designing experiments for reliable conclusions.
• Capability to bring frontier methods to production.

Nice To Haves

• Experience with multi-domain behavioral data (payment, mobility, food delivery, credit).
• Experience with temporal data scales from millisecond-level to daily/weekly.
• Expertise in pre-training objectives, tokenization architecture, scaling, multi-source data mixing ratios.
• Experience with Account-Card dual-dimension and cross-temporal-scale fusion.
• Expertise in contrastive learning, masked prediction, cross-modal fusion.
• Experience enabling one set of representations to serve multiple downstream scenarios.
• Experience in remote identity verification, liveness detection, comparison, and anti-attack.
• Experience supporting identity trust across the full chain of account opening and payment.

Responsibilities

• Own a frontier algorithm topic from research to production.
• Design, train, evaluate, and deploy algorithms.
• Be accountable for the online performance of algorithms.
• Define methodologies for solving complex problems using multi-domain behavioral data.
• Push the boundaries of algorithmic capabilities in fintech.
• Go deep in one direction and become its owner.
• Design experiments to reach reliable conclusions.
• Bring frontier methods to production.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed