AI & ML Engineer (Cybersecurity)
Cheltenham
Posted 6d ago
Job Location
Cheltenham
Tech Stack
Remote Work Policy
On-site
Categories
AI Agent Engineer
About the job
This role focuses on developing and optimizing AI agents and LLM-powered applications to enhance cybersecurity operations within a Security Operations Centre (SOC). The AI/ML Engineer will collaborate with security experts to design, build, and deploy AI workflows that integrate with existing security tools, aiming to accelerate threat detection and response. The mission is to leverage AI to combat evolving cyber threats, requiring a strong engineering background and a security-first mindset. The position involves architecting modular and scalable AI solutions, implementing robust security measures against adversarial attacks, and adhering to AI governance frameworks for data handling, logging, and compliance. Cost management for LLM usage and infrastructure is also a key aspect, alongside clear technical documentation.
Responsibilities
- Configure, evaluate, and tune LLMs for security use cases, including prompt engineering, RAG, and tool/function calling.
- Design, build, and maintain AI agents and agentic workflows using platforms like Azure AI Foundry, integrating with security tools (SOAR, SIEM, EDR).
- Implement safeguards against adversarial inputs like prompt injection and jailbreaks to ensure AI system security.
- Architect modular, maintainable, and scalable AI solutions following secure development principles.
- Implement AI solutions in line with governance frameworks, covering data handling, audit logging, human-in-the-loop controls, and compliance.
- Monitor and optimize LLM API usage and infrastructure costs through strategies like caching and guardrails.
- Collaborate with stakeholders to understand operational challenges, prototype solutions, and iterate based on feedback.
- Produce clear technical documentation for ongoing management of developed capabilities.
Requirements
- 2+ years of experience in AI/ML engineering.
- Hands-on experience building and deploying AI agents or LLM-powered applications in production.
- Practical experience with enterprise AI platforms (e.g., Azure AI Foundry, AWS Bedrock, Google Vertex AI).
- Strong understanding of LLM concepts (context windows, temperature, system prompts, tool/function calling) and vector databases.
- Experience implementing end-to-end RAG pipelines, including data ingestion, chunking, embedding model selection, and retrieval tuning.
- Experience implementing parsing pipelines for document processing and ingestion, including handling unstructured data.
- Demonstrable knowledge of AI security risks (e.g., OWASP LLM Top 10) and mitigation strategies.
- Experience working within enterprise governance frameworks.
- Proficiency in Python and familiarity with common AI/ML libraries.
- Ability to build custom tools for LLM interaction.
- Strong understanding of REST APIs and integrating AI solutions with third-party platforms.
- Experience with infrastructure-as-code is advantageous.
- Knowledge of enterprise security tooling (SOAR, SIEM, EDR) is advantageous.
- Collaborative, problem-solving, and self-motivated approach.