About the RoleAs a Machine Learning Engineer, you'll design the systems that make fraud detection possible — working across modeling, data pipelines, and backend systems (Go) to ensure ML models run reliably, efficiently, and at scale. This is a chance to combine applied ML with large-scale systems engineering, owning end-to-end solutions that tackle high-stakes, ever-evolving challenges.CompensationSalary: $175K – $220KEquity: Competitive equityVisa Sponsorship: Not available (TN: OK, L1/O1: Case-by-case, No H1-B)Work ArrangementFull-time, remote-first (US or Canada-based)Offices: Bay Area, NYC, Austin, Toronto, São PauloLocations: New York, San Francisco, South Bay Area, Los AngelesHiring Count: 3 openingsKey ResponsibilitiesBuild and optimize data pipelines and backend services to process device and behavioral data in real timeDevelop and deploy ML models for fraud detection, ensuring reliability and efficiency in productionTurn raw data into production-ready features that feed fraud detection systemsCollaborate with platform and backend engineers to integrate models seamlesslyMaintain high standards of security, privacy, and complianceChampion best practices in testing, documentation, and observabilityMandatory RequirementsSeniority: 5–8 years of software engineering experience with strong backend (Go or Python) and ML workWork Experience: End-to-end ML model ownership — feature pipelines, model deployment, monitoring, iteration (not just experimentation)Fraud domain experience required (bot detection, device fingerprinting, VPN/proxy detection, etc.)Hard Skills: Built latency-sensitive ML systems serving real-time predictions at scaleFamiliarity with ML platform tooling: feature pipelines, drift monitoring, model iteration cyclesHands-on applied ML with large datasets (PyTorch, Scikit-learn, etc.)Strong SQL skills with relational and non-relational databasesSoft Skills: Self-directed — navigates ambiguity and delivers with minimal hand-holdingCommunication: Excellent written and verbal English skillsEducation: BS or MS in Computer Science, Engineering, or related fieldLocation: Must be based in US or CanadaVisa: TN or L1/O1 (case-by-case); no H1-B sponsorshipBonus PointsFraud, risk, or cybersecurity domain knowledgeCI/CD, Docker, Kubernetes, modern DevOps frameworksModern browser APIs and high-entropy data collection techniquesLeveraging frontier LLMs for automationExperience with Go for backend services (or ability to pick up new languages quickly)Tech StackGo, Python, SQL, Docker, KubernetesTraits to AvoidNot just ML Ops — pure model-building with no production deployment or infrastructure experienceDepth in backend software engineering over data science preferredIdeal BackgroundFraud & Risk: Sift, Featurespace, Feedzai, Socure, Riskified, Unit21, Alloy, Vanta, DoppelCybersecurity: Palo Alto Networks, CrowdStrike, SentinelOne, Darktrace, Vectra AIFinTech: Stripe, Block, PayPal, Plaid, Adyen, Brex, Taktile, Middesk, FlareTrust & Safety: Google, Meta, Amazon, Apple, Netflix