Socure · Carson City, NVremote

Salary
$191,000–$230,000
Posted
Jul 15, 2026
Location
Carson City, NV
Last confirmed open
Jul 21, 2026

What this job asks for AI summary

A senior individual-contributor data science role focused on converting large-scale device, network, browser, mobile, and behavioral telemetry into production fraud and identity risk signals. The work spans signal development, feature engineering, model evaluation, and adversarial robustness, with cross-functional influence over telemetry collection and data architecture. The role also carries a mentorship responsibility, raising the technical standards of the broader data science team. Suited to a seasoned applied ML practitioner with a background in adversarial or fraud domains.

Staff level · 12+ years · Remote · Master's required · Full-time

Must have (10)
PythonSQLSparksupervised learningunsupervised learninganomaly detectionfeature engineeringmodel evaluationproduction ML monitoringfraud detection
Nice to have (6)
scikit-learnXGBoostTensorFlow or PyTorchdevice fingerprintingbehavioral biometricsadversarial ML

“or” means any one of them counts — you don't need all of them.

We read this from the posting text with AI. Skim the description below before ruling yourself out.

How this req sits in the market our data

Roughly 290 people nationally plausibly meet what this posting asks for (data scientists). range 60–440

Applicant volume Moderate — A normal amount of company. The rare requirements below are what will separate a shortlisted application from the rest.

What gives you an edge
anomaly detection5%

Rare in this occupation — lead with these, and say what you built with them.

What won't set you apart
Python88%SQL72%feature engineering50%

Most people in this occupation already list these. Still required — just not what gets you shortlisted.

What the occupation pays Median $122,874 (middle half $87,544–$162,374).

Estimated from BLS employment for this occupation and area, per-skill prevalence across our listing corpus, and published wage benchmarks — as of Jul 28, 2026. It is a model, not a headcount.

Why we read it this way (11)

The JD hard-requires a Master's or Ph.D. in a quantitative field; equivalent experience is not offered as a substitute, so the degree requirement is set to Masters (the minimum of the two stated options).

The 12+ years requirement is stated at the role level against no specific technology and is captured as the overall experience minimum.

'Spark, PySpark, or equivalent' is treated as a single hard-gated capability with PySpark listed as an alternative; the open-ended 'equivalent' is covered by the alternatives field.

Supervised learning, unsupervised learning, anomaly detection, feature engineering, model evaluation, and production monitoring are listed as a compound requirement under the hard-requirements section; each is a distinct modeling capability and is emitted separately.

Fraud detection / adversarial domain experience is explicitly required; identity verification, trust & safety, cybersecurity, and risk modeling are named as acceptable alternatives but fraud detection is the primary framing.

ML frameworks (scikit-learn, XGBoost, TensorFlow, PyTorch) appear only under Preferred Qualifications and are marked preferred accordingly.

Device fingerprinting, behavioral biometrics, graph-based risk signals, streaming/near-real-time ML, and adversarial ML all appear exclusively under Preferred Qualifications.

No compensation figures are provided in the posting.

Remote status is set per caller declaration; no metro is inferred.

Ignored 2 non-technology phrase(s) as skills (responsibilities/concepts, not named tools): graph-based risk signals, streaming / near-real-time ML.

Caller marked this a fully-remote role — scored against the national candidate pool.

Read the full posting

The employer publishes the full description on their own site — read it there ↗. Or sign in to read it here — it's free, and it also lets you track this application.

Apply

Apply on employer site ↗