Skip to main content

AI Security Engineer, Anthropic COE

slalomDenver, COSenior L5
Overview: As an AI Security Engineer, you will build and secure Claude deployments and Claude-powered security solutions across enterprises. You’ll implement, configure, and harden Claude components, integrate MCP-based workflows, and develop production-ready security capabilities. You’ll drive AI-enabled security operations, from discovery to remediation, while delivering reusable code and accelerators for Slalom’s AI security offerings. This role blends hands-on delivery with collaboration across AI security architects, client teams, and partner ecosystems, offering impact at scale. Compensation / Benefits flexible time off health/dental/vision coverage retirement 401(k) match parental leave well-being reimbursement disability coverage
Responsibilities: Deploy and securely configure Claude Enterprise, Claude Code, Claude API, and cloud-hosted Claude (Bedrock, Vertex AI, Azure) including access controls, data retention, and logging Build, deploy, and secure MCP servers and tool integrations with proper authentication, least privilege, and secrets management Implement agent security controls: sandboxing, scoped credentials, human-in-the-loop approvals, rate limiting, and policy enforcement Develop Claude-powered security automations (agentic vulnerability management, alert triage, threat intelligence enrichment) using the Claude Agent SDK and MCP Integrate Claude solutions with vulnerability scanners, EDR, SIEM/SOAR, ticketing, source control, and CI/CD via APIs and infrastructure as code Perform hands-on AI security testing (prompt injection, data leakage, jailbreak) and build automated test harnesses for guardrails Instrument usage with logging/telemetry, build detections and dashboards in SIEM, and provide visibility into agent actions Embed secure coding, dependency scanning, and secured CI/CD pipelines into AI solution delivery Configure cloud infrastructure hosting Claude (IAM, networking, encryption, key management, logging) Own technical delivery, troubleshoot, and translate architectures into documented, supportable solutions Build demos, POCs, and scoping support as a hands-on Anthropic and AI security expert Create reusable code, MCP connectors, deployment templates, and runbooks; stay current on Claude capabilities Coach and upskill consultants on Claude engineering, secure agent development, and AI security testing
Key requirements: Bachelor’s degree in Computer Science, Information Systems, Cybersecurity, or related field, or equivalent practical experience 8+ years of security or cloud security engineering experience Hands-on experience deploying and building with Claude (Enterprise/Code/API) and Claude Agent SDK, including deployments on Bedrock/Vertex/Azure Strong programming skills in Python and/or TypeScript with API/integration/automation experience Experience with agentic AI workflows, MCP servers, tool calling, and retrieval-augmented generation (RAG) Experience testing and mitigating AI-specific threats (prompt injection, data exfiltration, excessive agency, insecure tool use) Foundational cloud security knowledge (IAM, networking, encryption, key management, logging) Experience with security operations tooling (vulnerability management, SIEM/SOAR, EDR, application security) Experience with Git, CI/CD, containers, and infrastructure as code (Terraform) Strong communication skills for documenting work and explaining to diverse stakeholders Experience as Forward Deployed Engineer and leading FDE teams preferred strong communication collaboration mentorship Claude deployment and hardening MCP server engineering agent-based security tooling
APPLY NOW (opens in a new tab)

Matching similar jobs

Level

Senior L5

Location

Denver, CO

Occupation

Information Security Engineers

Industry

Computer Systems Design Services

Posted

today

APPLY NOW (opens in a new tab)