Senior Security Engineer (AI Safety), London, Lausanne

Isomorphic Labs
London
Workplace: HybridFull timeFunction: CybersecuritySkills: ["Collaboration","Communication","Risk assessment","Navigating ambiguity","Relationship building"]

Architect and secure Isomorphic Labs’ AI-first platform and autonomous agentic workflows in a high-stakes environment. Build AI-specific risk management frameworks, protect critical model artifacts, and implement scalable LLM guardrails with real-time monitoring. Lead AI security incident response, automate threat hunting and mitigation, and drive compliance governance automation aligned with emerging regulations. Collaborate across ML, platform, Legal, and Compliance to safeguard intellectual property while accelerating drug discovery.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Isomorphic Labs
Isomorphic Labs
2 months ago

Senior Security Engineer (AI Safety), London, Lausanne

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 6 hours agoStatus: Live

Job Summary

Architect and secure Isomorphic Labs’ AI-first platform and autonomous agentic workflows in a high-stakes environment. Build AI-specific risk management frameworks, protect critical model artifacts, and implement scalable LLM guardrails with real-time monitoring. Lead AI security incident response, automate threat hunting and mitigation, and drive compliance governance automation aligned with emerging regulations. Collaborate across ML, platform, Legal, and Compliance to safeguard intellectual property while accelerating drug discovery.
Location: London
Workplace: Hybrid
Employment Type: Full time
Job Function: Cybersecurity
Seniority: Sr. Manager level

Key Responsibilities

  • •Conduct AI/ML adversarial threat modeling and build a comprehensive risk management framework for an AI-powered life sciences platform.
  • •Partner with AI teams to inventory, classify, and protect ML model weights, code, and training data.
  • •Design and deploy scalable guardrails, sandboxing, and real-time monitoring controls for an LLM/agentic workflow ecosystem.
  • •Implement security controls across the ML lifecycle, from data ingestion and training pipeline integrity to inference runtime controls.
  • •Serve as primary technical expert for AI security incidents, automating threat hunting, anomaly detection, and mitigation specific to LLMs.

Key Requirements

  • •Deep conceptual and practical understanding of deep learning frameworks (e.g., JAX, PyTorch, TensorFlow) and large-scale cloud training/inference infrastructure plus LLM ecosystems.
  • •Strong familiarity with AI security threat vectors (prompt injection, model inversion, data poisoning) and frameworks like OWASP Top 10 for LLMs or MITRE ATLAS.
  • •Proven experience securing agentic frameworks (ADK, MCP) and implementing robust agent-to-agent (A2A) identity and access controls.
  • •Solid proficiency in cloud platform security (GCP preferred), including container security, multi-cloud/SaaS integrations, and strict network isolation boundaries.
  • •Ability to write production-grade code (Python preferred) to build custom security tooling and automate telemetry or enforce policy layers.
Experience:AI/MLLife sciencesBiotechPharmaDeep tech
Skills:CollaborationCommunicationRisk assessmentNavigating ambiguityRelationship building
Certifications:OSCPProfessional Cloud Security Engineer
Languages:English
Tech Stack:JAXPyTorchTensorFlowPythonGCPOWASP Top 10MITRE ATLASADKMCPLLMsEU AI Act

Company Brief

Isomorphic Labs
Uses machine learning and computational biology to accelerate drug discovery and design novel therapeutics by modeling protein structures, mechanisms, and interactions to identify promising targets and candidates.
Industry: Biotech
Company Size: Medium (51 to 250 employees)
Growth: Growth Stage Startup
Headquarters: London, United Kingdom
Founded: 2021
WebsiteLinkedIn