Job description
📐 About this role
WRITER is seeking a Detection and Response Engineer to defend our AI/AGI platforms, training data, and deployed models against sophisticated and evolving threats.
At WRITER, protecting the integrity of our AI systems is as critical as advancing their capabilities. This role blends hands-on security engineering with strategic threat detection, ensuring our defenses evolve faster than the adversaries targeting our infrastructure. You’ll design advanced detections, automate rapid responses, and lead investigations into incidents affecting our AI stack—covering everything from GPU clusters to model inference endpoints.
You’ll be the operational heartbeat of our AI security posture, partnering across security, infrastructure, and research teams to detect attacks, orchestrate containment, and safeguard our most valuable intellectual property.
If you thrive on staying ahead of attackers and can turn cutting-edge AI threat intelligence into production-grade detection systems, we’d love to hear from you.
Role Boundaries & Collaboration
What You Own (Responsible)
Incident response coordination
Real-time threat monitoring and detection
Production AI monitoring (not research)
Forensic investigation
Detection engineering across all security domains
AI threat detection implementation
What You Don’t Own (Others Lead)
AI security research (AI Security owns)
Preventive security controls (respective domain teams own)
Customer-facing security features (Software Security Engineering owns)
Infrastructure hardening (Cloud/Infrastructure owns)
Key Partnerships
With AI Security: They provide threat research and models; you implement production monitoring
With All Security Teams: You detect attacks across all domains; they build preventive controls
With Cloud/Infrastructure: They build infrastructure; you monitor it for threats
With Software Security Engineering: You detect customer-impacting incidents; they build protections
🦸🏻♀️ Your responsibilities
Engineer advanced threat detection — Design and implement detections for AI/ML-specific threats including prompt injection, model extraction, data poisoning, and adversarial inputs.
Automate security responses — Build playbooks and orchestration workflows that contain AI-targeted attacks in minutes, not hours.
Lead AI incident response — Coordinate cross-team investigations into compromises of models, training data, and inference endpoints.
Hunt for AI-specific threats — Proactively search for active attacks across GPU clusters, training pipelines, and model deployments.
Enhance visibility & telemetry — Onboard, optimize, and analyze logging from AI infrastructure to detect anomalies and misuse.
Collaborate across domains — Partner with AI Security on threat intelligence, Cloud/Infrastructure on runtime monitoring, and Software Security Engineering on customer-impacting incidents.
⭐️ Is this you?
Required Experience
8+ years in security operations, detection engineering, or incident response.
3+ years securing AI/ML infrastructure or high-performance computing environments.
Proven ability to detect and stop sophisticated attacks.
Experience with distributed systems, GPU cluster security, and cloud-native monitoring.
Proficiency with SIEM platforms and detection technologies.
Strong programming skills in Python, KQL, SPL, or similar.
Technical Expertise
Deep understanding of AI/ML attack vectors such as adversarial examples, model inversion, and membership inference.
Experience securing training pipelines, model deployments, and sensitive research environments.
Knowledge of GPU computing security challenges.
Hands-on forensics experience in distributed or cloud-based systems.
Execution & Impact
Demonstrated success in building detections for novel, AI-specific attack techniques.
History of safeguarding high-value intellectual property.
Proven record of automating incident response at scale.
Track record of uncovering critical security gaps through proactive threat hunting.
Preferred Qualifications
Background in AI/ML engineering or research.
Experience with AI safety and AI/ML security research.
Familiarity with APT tactics targeting AI companies.
Contributions to the AI security research community.
Experience with confidential computing or secure enclaves.
🍩 Benefits & perks (UK full-time employees):
Generous PTO, plus company holidays
Comprehensive medical and dental insurance
Paid parental leave for all parents (12 weeks)
Fertility and family planning support
Early-detection cancer testing through Galleri
Competitive pension scheme and company contribution
Annual work-life stipends for:
Home office setup, cell phone, internet
Wellness stipend for gym, massage/chiropractor, personal training, etc.
Learning and development stipend
Company-wide off-sites and team off-sites
Competitive compensation and company stock options
