At Unity Technologies SF, you will help protect Ads and Offerwall payouts by bringing machine learning from concept to production. This on-site role in Mountain View, CA is focused on real-time fraud prevention, modern ML training and serving, and building the labeled data and evaluation rigor the team relies on.
What you’ll do
- Ship fraud models to production: Move real-time anomaly detection and device risk models from development into production systems so model outputs drive payout and blocking decisions.
- Build and maintain the ground truth: Create and evolve a golden labeled fraud dataset, along with the evaluation methodology and baseline fraud-efficacy metrics used to assess model and rule changes.
- Own features end to end: Design and improve streaming and batch features that feed a Redis online feature store, partnering with data engineering on freshness, correctness, and lineage.
- Modernize ML infrastructure: Lead improvements to the training and serving stack, including evaluating a transition from AWS SageMaker to Kubeflow and KServe, with a focus on low-latency scoring in the real-time path.
- Detect new fraud patterns: Investigate fraud spikes, analyze user and device behavior, and convert findings into new signals, features, and models.
- Operate and document: Monitor model and feature health in production, write runbooks and data lineage documentation, and participate in on-call for the fraud detection stack.
What you’ll bring
- Production ML experience: Several years building ML models and taking them through deployment, monitoring, and iteration after launch.
- Fraud, risk, or anomaly detection: Hands-on experience with fraud detection, abuse prevention, risk scoring, or anomaly detection, including work with sparse, noisy, or adversarial labels.
- Real-time serving and feature engineering: Experience with low-latency model serving and online/offline feature pipelines (for example Redis online feature stores, Kafka streaming, and Airflow).
- Evaluation rigor: Ability to build labeled datasets from imperfect signals and design evaluation methods that remain reliable as fraud patterns shift.
- Core technologies: Strong Python and SQL, with working knowledge of cloud ML platforms such as AWS SageMaker, Kubeflow, or KServe.
- Ownership and collaboration: Comfort working from ambiguity to shipped outcomes with limited oversight, documenting work, and collaborating across backend, data, and product teams. Experience using AI coding tools to move faster.
Tools you’ll work with
Python, SQL, Redis, Kafka, Airflow, AWS SageMaker, Kubeflow, KServe, Kubernetes
Benefits at Unity
- Comprehensive health, life, and disability insurance
- Commute subsidy
- Employee stock ownership
- Competitive retirement/pension plans
- Generous vacation and personal days
- Support for new parents through leave and family-care programs
- Office food snacks
- Mental Health and Wellbeing programs and support
- Employee Resource Groups
- Global Employee Assistance Program
- Training and development programs
- Volunteering and donation matching program
Salary range
- Zone A: $178,700 - $232,300 (base yearly)
- Zone B: $159,100 - $206,800 (base yearly)
- Zone C: $140,700 - $182,900 (base yearly)
Additional details
Beyond base salary, this role may be eligible for equity awards and participation in company incentive plans, such as annual discretionary bonuses or sales commissions. Final offer amount depends on geographic location and the candidate’s relevant experience, professional background, and skill set.
You might also have
- Experience with ad fraud, install/attribution fraud, or fraud in rewarded or incentivized advertising
- Experience with unsupervised or semi-supervised detection methods such as autoencoders, isolation forests, or graph-based approaches to device and user linking
- Experience migrating ML serving between platforms or building MLOps tooling on Kubernetes
- Background in mobile ad tech, mobile games, or app monetization
Eligibility statements: Benefits eligibility, specific offerings, and coverage vary based on country and employment status. This position requires sufficient knowledge of English for professional verbal and written exchanges. Pursuant to the San Francisco Fair Chance Ordinance, Unity will consider for employment qualified applicants with arrest and conviction records. Headhunters and recruitment agencies may not submit resumes/CVs through this Web site or directly to managers. Unity does not accept unsolicited headhunter and agency resumes.
