← All roles

Data Scientist, Antifraud

Higgsfield AI· Product Engineering
Apply on company site
Almaty, KazakhstanFull-timePosted 3w ago

About the role

Data Scientist focused on antifraud detection and enforcement in a generative AI/video platform. Owns account-abuse scoring, entity resolution, enforcement policies, measurement, and usability of security tooling to prevent abusive utilization before compute is spent.

Responsibilities

  • Own the account-abuse scoring system end to end: signals, weights, thresholds, the scoring job, the monitoring, and the recalibration when it decays.
  • Build detection that fires early with measurable impact and cost awareness.
  • Work the linkage and economics aspects to ensure robust fraud detection at account level.
  • Treat cost as a gate, not a label, especially on unlimited plans.
  • Find rings, not just accounts: shared payment instruments, IP/ASN concentration, email-stem families, synchronised registration bursts, behavioural fingerprints, automation signatures.
  • Do it without a reliable device fingerprint and evaluate what such a fingerprint would cost/value.
  • Know where graph methods break and avoid over-aggregating unrelated users.
  • Design graduated, reversible actions (throttle, rate-limit, step-up verification, hold, pre-grant refusal, manual review queue, ban).
  • Own the false-positive budget explicitly and define the appeal path for false positives.
  • Build pre-grant gates and collaborate with Payments, Support, and Legal.
  • Quantify system value in money, monitor holdouts, watch for adversarial adaptation, and ensure inputs are reliable.
  • Ship scores with reasons and produce auditable evidence for external use.
  • Work in SQL, Python and BigQuery on raw event, payment and generation data; leverage AI as needed.

Qualifications

  • Experience building abuse, fraud or trust-and-safety detection that actually took action on real users (payments fraud, promo abuse, multi-accounting, etc.).
  • Strong SQL and Python on raw event data; ability to join payments, usage and identity data; proficiency with window functions and cohort analysis.
  • Experience with graph and linkage thinking: connected components, shared-attribute clustering, and discerning evidence vs. coincidence.
  • Precision-first evaluation mindset: cost-weighted error, precision at operating point, and justification for enforcement choices.
  • Unit-economics literacy: understanding gross margin per account and compute costs.
  • Clear written and spoken English (B2+).

Skills

Required:SQLPythonGraph and linkage thinkingEvaluation & metricsDomain knowledge in fraud/riskCommunication

Benefits

  • Competitive salary in USD
  • Equity participation in stock option program
  • On-site role in Almaty, Kazakhstan
  • Relocation support (flight + temporary housing)
  • Flat structure, high autonomy, fast career growth
Last updated Oct 25, 2026. Interested? Apply on the company site.
Higgsfield AI logo

About Higgsfield AI

Higgsfield AI — AI-native creative suite

Create images, videos, and voice content with Higgsfield AI from text prompts or references. Edit and upscale media, automate creative workflows with its AI agent, and generate content on web and mobile.

AI-native creative suiteAppsSeedanceSeedreamMCP & CLIGemini Omni FlashCinema StudioOriginal Series
Company profileWebsite

More open roles at Higgsfield AI