AI-Assisted Cyber Analysis Specialist

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a AI-Assisted Cyber Analysis Specialist based in United States. The AI-Assisted Cyber Analysis Specialist will design and operate governed, human-in-the-loop workflows that accelerate the analysis of complex cybersecurity data and artifacts. The role combines hands-on cybersecurity expertise with Python automation and approved AI/ML or agentic technologies to improve the speed and quality of security analysis. You will work with large volumes of source code, configurations, scan results, vulnerabilities, evidence, and other security artifacts while maintaining accuracy, confidentiality, provenance, and reproducibility. The position supports continuous technical assessments of federal cyber assets, helping identify unknown exposures and validate vulnerabilities across internet-facing environments. You will collaborate closely with security analysts to present structured findings, communicate uncertainty, and incorporate human feedback into ongoing workflow improvements. This is an applied cyber-analysis position in a mission-focused environment where secure AI adoption and rigorous technical controls are essential.

Accountabilities

• Design human-in-the-loop AI-assisted workflows to classify, enrich, correlate, summarize, and prioritize large volumes of cybersecurity artifacts, including code, configurations, findings, scan results, and supporting evidence.
• Build and maintain Python-based services, tools, APIs, prompts, schemas, retrieval pipelines, and evaluation frameworks using customer-approved AI model endpoints and data stores.
• Integrate deterministic security technologies and rules, including SAST/DAST, Semgrep, YARA, Sigma, SBOM, vulnerability, and configuration analysis, with AI-assisted workflows rather than relying solely on model-generated outputs.
• Establish measurable quality controls by monitoring precision, recall, false positives, false negatives, latency, cost, workflow drift, and analyst time saved, while documenting acceptance thresholds and rollback procedures.
• Protect sensitive information through appropriate access controls, approved model boundaries, provenance tracking, audit logging, redaction, prompt-injection defenses, and secure handling of untrusted code and artifacts.
• Present structured findings and uncertainty to security analysts, facilitate manual validation, and incorporate analyst feedback into continuous workflow improvement.
• Maintain technical documentation, test datasets, workflow and model versions, and reproducible release processes.
• Provide continuous technical assessment support for federal cyber assets, including .gov domains, subdomains, and internet-facing systems, to identify exposures, validate vulnerabilities, and support actionable remediation guidance.

Requirements

• U.S. citizenship is required, along with eligibility to access sensitive information and the ability to obtain a High Risk Public Trust fitness determination.
• Ability to work within customer-provided remote environments, use approved tools, and comply with rules of engagement, data-handling requirements, evidence controls, deconfliction procedures, and stop-work criteria.
• Five or more years of combined experience in cybersecurity analysis, security engineering, software or data engineering, or applied AI/ML, including experience delivering production automation used by analysts or operators.
• Strong Python, API development, data-processing, testing, and source-control skills, with experience managing structured and unstructured technical artifacts at scale.
• Practical knowledge of vulnerability assessment, attack paths, source-code or configuration analysis, malware or security-artifact triage, or security-tool outputs sufficient to validate analytical results.
• Demonstrated experience building and evaluating AI/ML or LLM-assisted workflows with explicit human review, grounding and provenance, structured outputs, and measurable quality controls.
• Understanding of AI security risks, including data leakage, prompt injection, untrusted content, model hallucination, authorization, auditability, and secure deployment.
• Strong communication skills, with the ability to explain technical limitations and uncertainty clearly and produce maintainable technical documentation.
• Experience with agentic workflow frameworks, retrieval-augmented gene…