Kodex
Technology
MLEngineer-Verifications
Neural analysis suggests this role is
optimal for Mid+ candidates.
“ML Engineer - Verifications at Kodex. Skills: ML Engineering, Threat Intelligence, Data Security. Build models to detect suspicious behavior. Build models to flag suspicious behavior”
What You'll Achieve.
Detect suspicious activity; Improve verification accuracy; Turn signals into systems; Strengthen compliance; Enhance security; Reduce operational costs
Industry & Context.
Root cause analysis
What They're Looking For.
Must Have
4+ years building ML systems, Experience in fraud analytics, Experience in abuse analytics, Experience in trust & safety analytics, Experience in risk analytics, Experience in security analytics, Experience with ML/DS workflows, Experience deploying models, Comfortable with data pipelines, Comfortable with messy data, Think about reliability, Think about safety
Nice to Have
Familiarity with LLMs, Familiarity with RAG, Familiarity with agentic workflows, Experience in compliance-sensitive environments, Experience with privacy, Experience with access controls, Experience with audit trails
What You'll Do.
Build models to detect suspicious behavior
Build models to flag suspicious behavior
Own ML pipelines end-to-end
Perform batch inference
Perform streaming inference
Design evaluation strategies
Design monitoring strategies
Define ground truth strategies
Define offline metrics
Integrate intelligence into workflows
Improve data accessibility
Contribute to operational rigor
Implement safe rollout practices
How You'll Work.
Team & Collaboration
Threat Intel operators; Product engineers; Data engineering; Cross-discipline communication
Communication Scope
Communicate clearly
Process & Methodology
Problem framing, Experimentation
Full Job Description
About the company Kodex revolutionizes how organizations handle sensitive subpoenas and data requests from law enforcement and government agencies. Founded by a former FBI agent and backed by leading investors including Andreessen Horowitz, Y Combinator, Peak XV and Thiel Capital, Kodex has become the industry standard for secure data exchange. Our platform supports over 15,000 government agencies in 190 countries and is trusted by industry leaders like Coinbase, Stripe, and AT&T. By transforming a traditionally complex and manual process into a streamlined digital workflow, Kodex helps organizations strengthen compliance, enhance security, and reduce operational costs by millions each year. We bridge the gap between companies and authorized requestors, ensuring that sensitive data is handled with uncompromising security, transparency, and efficiency. About the Role We’re hiring an ML Engineer to join Kodex’s Verifications / Threat Intel org and help build the intelligence layer that protects our platform — detecting suspicious activity, improving verification accuracy, and turning messy real-world signals into scalable, auditable systems. This role sits at the intersection of product, data, and security. You’ll partner closely with Threat Intel operators and engineers to translate investigative workflows into production-grade models, pipelines, and decision-support tooling. You’ll also help evolve our current approach beyond noisy, brittle heuristics toward systems that are measurable, explainable, and safe to operate. What You’ll Do You’ll work across the full lifecycle — from problem framing and data exploration through deployment, monitoring, and iteration. Example areas include: - Build and deploy models to detect and flag suspicious behavior (classification, anomaly detection, clustering, ranking, and other approaches as appropriate) - Own ML pipelines end-to-end (feature generation, training, evaluation, batch/streaming inference, backfills, and versioning) -
Applying for this ML Engineer - Verifications role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Ashby
- Ashby is a fast modern ATS — most applications take under 3 minutes.
- The resume parser is strong; verify parsed experience dates and job titles.
- Custom screening questions are often scored algorithmically — answer completely.
- Location field affects geo-based screening; use your actual metro area.
ANONYMOUS · UNFILTERED
What do employees actually say about Kodex?
Real rants from real employees. Read before you apply.