Foundation Model AI Scientist for Real-Time Fraud (Remote)

Sardine; United States; Remote; USD 140,000 - 240,000; Full time

Benefits offered by this job

Generous cash and equity compensation

Remote-first culture

Flexible PTO and year-end break

Health, dental, vision insurance (US/2

401k matching

MacBook Pro provided

Home office setup stipend

Meal stipend

Social meet-up stipend

Annual health & wellness stipend

Annual learning stipend

Job summary

Sardine is hiring an applied research scientist to advance foundation models for fraud detection using rich non-text sequential data. You will scope experiments, drive model evaluation, and push end-to-end deployment with strict latency requirements in a remote-first environment.

You will collaborate across data science, engineering, product, and external partners, bringing strong Python/SQL skills, production ML experience, and a track record with foundation models to real traffic in the US or

Qualifications

• 4+ years in applied machine learning, quantitative modeling, or ML engineering including at least one foundation model you pre trained or substantially adapted and put in front of real traffic.
• Hands-on self-supervised pre training experience, plus practical fine-tuning and adaptation.
• Production experience with model serving, versioning, monitoring, and rollback.
• Ability to self-manage and drive ambiguous applied research projects with clear communication with partner teams across data science, engineering, product, marketing and external partners.
• Strong Python, strong SQL, and comfort preparing very large datasets.

Responsibilities

• Identify and scope opportunities, design rigorous experiments, and execute on the roadmap for foundation model research and development.
• Own the evaluation bar for foundation model performance: offline benchmarks, time- and entity-aware holdouts, calibration, drift and degradation monitoring, and honest head-to-head comparisons against strong classical baselines.
• Take models the full distance from data prep and tokenization through pretraining, fine-tuning, distillation, quantization, and deployment behind a real-time inference path with tight latency budgets.
• Partner with Engineering on training infrastructure, GPU efficiency, feature and embedding stores, and serving at production scale
• Work directly with client-facing teams and customers to turn model capabilities and limits into decisions their risk teams can act on.
• Partner with Legal, Compliance, and customer model risk teams to build the explainability, documentation, and governance our bank and fintech customers need to satisfy their own regulators.

Skills

Python

SQL

Foundation models

Experiment design

Large datasets

Production ML

Job description

Sardine is hiring an applied research scientist to advance foundation models for fraud detection using rich non-text sequential data. You will scope experiments, drive model evaluation, and push end-to-end deployment with strict latency requirements in a remote-first environment.

You will collaborate across data science, engineering, product, and external partners, bringing strong Python/SQL skills, production ML experience, and a track record with foundation models to real traffic in the US or