SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Writer is an enterprise generative AI platform valued at $1.9B, backed by leading investors, serving hundreds of companies including Mars, Marriott, Uber, and Vanguard. The company is building AI agents grounded in enterprise data and powered by enterprise-grade LLMs.
You will join Writer's security team as a Staff Detection and Response Engineer, responsible for building sophisticated detection systems and automated response capabilities to protect the company's AI infrastructure, training data, and model deployments. This role combines hands-on security engineering with strategic threat intelligence work, focusing on novel AI-specific threats that evolve rapidly alongside AI advancement.
Key responsibilities include:
- Design and implement detection strategies for AI-specific threats including prompt injection, model extraction, data poisoning, adversarial examples, and unauthorized access to training datasets or model weights across distributed infrastructure
- Build automated response playbooks and orchestration workflows that contain threats without human intervention, reducing mean time to response from hours to minutes and automatically remediating compromised inference endpoints
- Lead security incident response coordination across Cloud, AppSec, Enterprise, and AI Security teams when AI infrastructure or models are compromised, conducting forensic investigations on training pipeline attacks and model manipulation attempts
- Conduct proactive threat hunting across GPU clusters and training infrastructure by analyzing model outputs for compromise signs, reproducing AI-specific vulnerabilities, and identifying visibility gaps before adversaries exploit them
- Build detection-as-code frameworks with version control and automated deployment, onboard telemetry from AI training infrastructure and inference endpoints, and create dashboards tracking model security metrics and access to sensitive research data
- Serve as operational security partner across all teams, translating AI Security's threat research into production detections, monitoring GPU clusters, detecting customer-impacting incidents, and enabling responsible AI development through security guardrails
- Maintain 24/7 on-call rotation for critical AI security incidents, responding to real-time threats while continuously improving detection coverage and automation
Requirements:
- 3–5+ years in security operations, detection engineering, or incident response with proven track record of identifying and stopping sophisticated attacks in production environments
- 3+ years specifically securing AI/ML infrastructure, high-performance computing environments, or other distributed systems at scale
- Strong programming skills in Python, KQL, SPL, or similar languages to build custom detection logic, automate response workflows, and operationalize security across cloud-native and distributed computing environments
- Experience with SIEM platforms, detection technologies, and forensic investigation techniques; demonstrated ability to build detection for novel attack techniques without established patterns and conduct forensics in complex distributed environments
- Self-directed execution mindset with track record of securing high-value intellectual property, automating incident response in complex environments, and identifying critical security gaps through proactive threat hunting
- Deep alignment with Writer's values: ability to connect across security, infrastructure, and AI research teams; willingness to challenge assumptions about AI security engineering; ownership mentality for protecting the AI platform with accountability and commitment to staying ahead of evolving threats
About Writer
AI / Data / Infrastructure; SaaS / Enterprise Software — enterprise generative AI platform for business teams.
