Machine Learning Engineer

About the company

Our client is a fintech company.

The role

Raydar is recruiting for this role on behalf of our client. Design, train and deploy machine learning models that make real-time risk calls in a payments setting, owning the data pipelines, evaluation and metrics behind them. The role leads modeling work as an individual contributor, with room to build and manage a team over time.

What you'll do

- Own the data pipelines and modeling design for core models, including a small language model used for contextual understanding.

- Convert plain-language user approvals into structured, checkable limits covering vendors, amounts, items and time windows.

- Score automated actions in real time to flag drift, substitutions, injection attempts and overspending before funds move.

- Make risk calls from identity, user history, device and vendor signals, choosing whether to approve, request confirmation or refuse.

- Own evaluation, labeling and metrics, tracking false approvals and false blocks as product measures.

- Ship models into production paths with tight latency and cost budgets.

Requirements

What we're looking for

- 2 to 5 years of experience in machine learning or related engineering work.

- A hands-on record of training machine learning or language models, ideally including one that has operated live and driven consequential calls for users.

- Proficiency in Python and TypeScript.

- Sound judgment about where large language models are reliable, where they fail, and how to measure it.

- A habit of designing evaluations before building models, and of shipping models they have built themselves.

- Strong working knowledge in one specialty: scoring suspicious activity for fraud, building rule engines that grant or deny access, or testing and safeguarding language model outputs.

- Comfort with a roughly six-day, in-office week (Sunday through Friday).

Benefits

Compensation and benefits

- Base salary: USD 140,000 to 300,000 per year

- Health, dental and vision coverage

Location and work model

- San Francisco, California, United States

- On-site, roughly six days a week in office (Sunday through Friday), with flexibility on weekends

- Full-time