AI Two-Sided Market Trust Developer

Intevo AI

Remote · $160k – $200k / year · Full-time · Posted 5 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Trust in a two-sided marketplace is hard to measure and easy to destroy. A buyer who gets scammed does not just churn — they leave reviews, tell friends, and the trust damage compounds. A seller who gets falsely flagged does not just appeal — they post publicly and the resulting PR incident costs more than the prevented fraud. Getting trust scoring right on both sides simultaneously is the central product challenge for any marketplace. Our marketplace serves 2.8 million active users across buyer and seller sides. The current trust system scores each side independently. What is missing is a joint model: one that understands the trust dynamics of specific buyer-seller interaction patterns, that learns from resolved dispute outcomes rather than just reported incidents, and that handles the cold-start problem for new participants who have no history. You will own the joint trust model architecture — designing the interaction-level features, building the dispute outcome feedback loop, and developing the cold-start trust signals that combine profile completeness, payment method risk, and behavioral patterns from the first few sessions.

Fully remote.

Responsibilities

Design joint trust model capturing buyer-seller interaction risk patterns
Build dispute outcome feedback pipeline for closed-loop trust signal improvement
Develop cold-start trust scoring for new participants with no transaction history
Implement trust score monitoring and drift detection across user cohorts
Design appeals workflow that uses model uncertainty to route borderline cases
Collaborate with trust and safety operations team on investigation workflows

Requirements

6+ years in ML engineering with marketplace trust, fraud, or risk domain experience
Experience building two-sided market models or interaction-level risk systems
Strong Python, PyTorch, and Spark skills for large-scale user event processing
Deep statistical knowledge for trust signal design and evaluation
Track record shipping ML systems with direct business impact in marketplace settings