À propos de ce poste Backend Software Engineer, Trust & Safety (Anti-Fraud) chez Higgsfield
Almaty, Kazakhstan · Trust & Safety Engineering
Why this role exists
Our ML and analytics teams already work on fraud detection and risk analysis. This role owns the backend that turns their signals into reliable protections across accounts, credits, payments, and generation. You'll integrate risk checks into product flows, build enforcement services and operator tools, and make sure controls work correctly in production. We're looking for an engineer we can trust to take a backend problem from an unclear starting point to a working solution.
What you'll actually do
Risk integrations: connect existing ML scores and risk signals to account creation, credit usage, payments, and generation flows, with clear timeouts and fallback behavior.
Enforcement services: implement configurable rules, rate limits, account restrictions, and credit or payment controls with consistent behavior across services.
Operator tooling: build APIs and workflows for reviewing cases, inspecting decision history, and safely applying or reversing restrictions.
Production reliability: handle retries, duplicate events, concurrent requests, and safe rollouts; add monitoring and audit trails so failures can be traced and fixed.
Work in other teams’ codebases to add signals or interventions without hurting their stability or architecture.
Ownership: clarify the control with ML, analytics, and operations → scope the smallest useful implementation → ship → verify production behavior and review impact with the team. Our release cycle is days, not quarters, so your first shipped protection happens fast.
Must-haves
You've taken a difficult problem from an unclear starting point to a working system used in production, and can explain your own decisions, contribution, and results.
You can build reliable backend services: APIs, data models, queues, transactions, idempotency, and concurrency. You can integrate external services and debug failures across the request and event lifecycle.
You choose the next steps, remove blockers, and ask for help when needed. You cut scope to test an idea, adapt from evidence, and keep working through difficult problems.
You work with ML, analytics, and operations to turn risk requirements into clear backend behavior. You use operator feedback and customer cases to improve controls and learn unfamiliar systems quickly.
You take feedback, change your mind when the evidence changes, and do the work the team needs. You share knowledge and responsibility so others can operate and extend what you build.
Who this is not for
You prefer problems where requirements stay stable after launch.
You prefer work centered on training models or producing analysis rather than building and operating backend services.
Nice to have
Fraud prevention, payments risk, or platform abuse experience.
Integrating risk-scoring services or building rules engines and rate limiters.
Case management, appeals, and risk operations tooling.
Familiarity with Stripe.
Experience building real-time scoring, graph-based account linkage systems.
Python/Go experience.
Interview process
Recruiter screen: role expectations, logistics, and fit.
Technical interview: a difficult system you shipped, what you personally decided and built, and how your work made the team more capable without leaving it dependent on you.
Additional technical interview, if needed: a deeper discussion of technical skills and open questions.
Product fit interview: take an existing risk signal and an operator need, scope a backend protection, and work through failure cases and effects on legitimate customers.
Offer.
What we offer
Competitive base in USD, equity, relocation support, and ownership of protections that preserve both company revenue and customer trust.
