Senior/ Principal Data Scientist, Security AI & ML

RADICL•Boulder, CO, CO

1d•$160,000 - $235,000•Hybrid

About The Position

RADICL is hiring a Senior- or Principal-level Data Scientist to improve and extend AI and machine-learning capabilities already in production in its cybersecurity and compliance platform. RADICL provides a fully managed service to small and mid-sized organizations, including defense contractors facing nation-state threats and CMMC requirements. Its autonomous virtual SOC combines AI agents for high-volume triage with expert analysts for judgment and response. This is a hands-on role involving writing code, running experiments, and shipping models. The Data Scientist will evaluate AI agents against analyst verdicts, improve triage, investigation, and search agents, and decide when to customize or train models using analyst-labeled data. The role also develops behavior-based threat detection across security data sources and protects AI agents from attacker-controlled input. Success is demonstrated in production through measures such as time to triage, analyst override rate, and false-positive load. The position owns model versioning, monitoring, customer data isolation, and audit-traceable outputs. The role offers the opportunity to choose methods and tools and build solutions using security telemetry at scale, analyst-labeled cases, and AI agents already in production. It contributes to defending defense suppliers and other high-risk small organizations from nation-state threats. RADICL describes its environment as fast-paced and collaborative, with close work alongside an experienced founding team.

Requirements

At least 6 years of data science or applied machine-learning experience for Senior level, or at least 8 years for Principal level.
Experience shipping and maintaining models in production.
Strong Python and SQL skills.
Experience with large-scale data processing on a major cloud platform.
Experience evaluating and improving LLM or agent systems in production.
Hands-on experience adapting or training models for a specialized domain.
Experience with anomaly detection or classification involving rare events and noisy labels.
Strong statistics and experimental-design skills, with judgment to use a simple baseline when appropriate.
Comfort working in an engineering team, including reading production code, writing tests, and writing clear RFCs.
For Principal level: experience owning ML problems end to end and defending architecture decisions for the ML stack.

Nice To Haves

Security data and detection experience, including MITRE ATT&CK.
LLM security experience, including prompt injection, guardrails, or agent red-teaming.
Experience with vulnerability data such as CVSS or EPSS, or with CMMC / NIST 800-171.

Responsibilities

Define how AI agent performance is evaluated, measure results against analyst verdicts, and gate changes on evaluation outcomes.
Improve the quality, speed, and cost of triage, investigation, and search agents.
Determine when to customize or train models using analyst-labeled data, and carry out that work.
Build models that detect threats missed by rules across endpoint, identity, email, cloud and SaaS audit, network, and vulnerability data.
Protect AI agents from manipulation by attacker-controlled data.
Measure AI effectiveness in production using measures such as time to triage, analyst override rate, and false-positive load.
Own model versioning and monitoring, ensure strict per-customer data isolation, and maintain traceable outputs suitable for CMMC audits.