Senior Machine Learning Engineer, Behavioral Biometrics

Anthology Careers

. Build authorship verification models as an open-set verification problem .

Posted 10/9/2026full-timeRemote • United StatesSenior💰 $127,000 - $160,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and optimizing authorship verification models, with a strong focus on data extraction from keystroke telemetry and performance evaluation. Proficient in advanced Python programming and machine learning frameworks, ensuring effective model deployment and adherence to privacy practices.

Highest-signal resume keywords

Advanced Python ProgrammingExperience with Scikit-LearnFluency in PyTorchResearch Experience in Data ModelingUnderstanding of Evaluation Setups

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Authorship Verification ModelsKeystroke Telemetry AnalysisGradient-Boosted TreesLightGBMXGBoostRandom ForestsSequence ModelsData Collection and ValidationTechnical WritingModel Optimization

Soft Skills

Clear Technical WritingCollaboration with Engineers

Tools & Technologies

Scikit-LearnPandasNumPyPyTorch

Industry Keywords

Biometric Data PrivacyModel EvaluationSession-Leakage DetectionFalse Accept and Reject RatesTemporal Structure

Tech Stack

Tools & technologies

NumpyPandasPythonPyTorchScikit-Learn

About the role

Key responsibilities & impact

Build authorship verification models as an open-set verification problem
Extract signal from keystroke telemetry, including timing distributions, digraph and trigraph latencies, pause and burst structure, editing and revision behavior, and effort over time
Optimize models for edge inference on student laptops, including latency, memory, CPU, quantization, and runtime selection
Design defensible evaluations with subject-disjoint splits and session-leakage detection
Report false accept and false reject rates and measure performance across keyboard layouts, device types, non-native typists, and writers with motor differences
Probe resistance to replay and synthetic keystroke generation
Help establish privacy and fairness practices for biometric data
Partner with data and software engineers to move models from notebook to release and remain involved after launch

Requirements

What you’ll need

M.S. with 3+ years of related experience, or Ph.D. in Computer Science (or related field)
Direct research experience through graduate lab work, thesis research, or publications
Experience carrying a question from hypothesis through data collection, modeling, and validation
Advanced Python with fluency in scikit-learn, pandas, NumPy, and a deep learning framework such as PyTorch
Strong with gradient-boosted trees on engineered features, including LightGBM, XGBoost, and random forests
Comfortable using sequence models when temporal structure justifies the cost
Understanding of leakage, distribution shift, small-sample effects, and evaluation setups that flatter the model
Clear technical writing
Fluency in written and spoken English