01
TRCI-26-05291
AI/ML Security Engineer (Agentic/LLM Guardrails) - Contract
Contract role in London for an experienced cyber security engineer/architect with 5+ years in regulated environments (ideally banking/fintech) and 2+ years hands-on AI/ML security. The focus is securing agentic/LLM systems: threat modeling multi-agent orchestrations, building secure sandboxes and least-privilege execution environments, implementing real-time proxy guardrails against prompt injection/data exfiltration, running offensive simulations against agent reasoning/vector DB/memory layers, and creating detection/response engineering to isolate rogue agent threads. Strong Python and Go are required, plus CI/CD DevSecOps delivery in agile teams and awareness of relevant benchmarks and regulations (DORA, FCA/PRA).
Position summary
- Location
- United Kingdom
- Workplace
- Hybrid
- Employment
- Contract
- Experience
- Minimum 5 years and Maximum 7 years
Role overview
Why This Role Matters.
Contract role in London for an experienced cyber security engineer/architect with 5+ years in regulated environments (ideally banking/fintech) and 2+ years hands-on AI/ML security. The focus is securing agentic/LLM systems: threat modeling multi-agent orchestrations, building secure sandboxes and least-privilege execution environments, implementing real-time proxy guardrails against prompt injection/data exfiltration, running offensive simulations against agent reasoning/vector DB/memory layers, and creating detection/response engineering to isolate rogue agent threads. Strong Python and Go are required, plus CI/CD DevSecOps delivery in agile teams and awareness of relevant benchmarks and regulations (DORA, FCA/PRA).
Your Impact
Deliver Enterprise Value
Help organisations solve complex business problems through modern technology, consulting expertise and measurable outcomes.
Collaboration
Work Across Teams
Collaborate with consultants, architects, engineers and client stakeholders throughout the project lifecycle.
Growth
Learn Continuously
Gain exposure to enterprise technologies, certifications, mentoring and real-world project experience.
Career Path
Grow With Ubique
Build a long-term consulting career with opportunities to take on greater responsibility and leadership over time.
Responsibilities
What You'll Be Doing.
Every role at Ubique contributes directly to solving meaningful business challenges for our clients.
02
Perform advanced Digital Forensics on complex agent memory logs, tracking step-by-step reasoning patterns and API execution loops following anomalous events.
03
Embed security guardrails smoothly into production deployment loops using DevOps pipelines (CI/CD) and automated testing frameworks.
04
Operate within high-velocity teams using Agile Methodology & Tools (e.g., Jira, Confluence) to cleanly deliver tasks inside sprint timelines.
05
Maintain a mindset of Customer Centricity, ensuring that heavy security layers and model guardrails do not negatively disrupt the user experience.
06
Commitment to Continuous Learning, tracking the fast-evolving landscape of agentic frameworks (e.g., LangChain, AutoGen, CrewAI) and modern security benchmarks (MITRE ATLAS, OWASP Top 10 for LLMs).
07
DORA (Digital Operational Resilience Act): Ensuring operational resilience of autonomous systems under stress.
08
FCA & PRA Guidelines: Adhering to strict compliance for automated decision-making pipelines and accountability frameworks.
Technology stack
Tools & Technologies.
The platforms and technologies you'll use to build modern, enterprise-grade solutions.
01
AI security
Required
02
ML security
Required
03
LLM guardrails
Required
04
prompt injection
Required
05
indirect prompt injection
Required
06
data exfiltration
Required
07
adversarial machine learning
Required
08
agentic AI
Required
09
multi-agent orchestration
Required
10
tool-use vulnerabilities
Required
11
goal-jacking
Required
12
vector database
Required
13
memory layer
Required
14
security proxy
Required
15
sandbox
Required
16
secure execution environment
Required
17
least privilege
Required
18
detection engineering
Required
19
response engineering
Required
20
threat modeling
Required
Requirements
Skills & Experience.
We value curiosity, collaboration and continuous learning. If you don't meet every requirement but believe you can make an impact, we'd still love to hear from you.
Essential
Required Qualifications
5+ years in cyber security engineering/security architecture/detection engineering/DevSecOps in highly regulated environments
2+ years hands-on AI/ML security (LLM guardrails, adversarial ML, or security for automated execution pipelines)
Threat modeling for multi-agent orchestrations (tool-use vulnerabilities, autonomous execution manipulation, goal-jacking, cascading agent failures)
Security engineering of secure execution environments/sandboxes; strict least privilege enforcement
Real-time proxy guardrails to intercept malicious prompts, indirect prompt injection, and data exfiltration vectors
Offensive security testing simulating adversarial ML tactics against agent reasoning loops, vector databases, and memory layers
Detection engineering to identify anomalous agent behaviors, API misuse, and malicious intent vectors pre-execution
Response engineering/orchestration to isolate, throttle, or terminate rogue agent threads safely
Python (production-grade security proxies/wrappers/validation controls)
Go (production-grade security proxies/wrappers/validation controls)
DevOps/CI/CD integration of security guardrails and automated testing frameworks
Threat hunting for systemic poisoning/persistent manipulation/silent model exploitation
Digital forensics on agent memory logs and execution loops
Agile delivery using Jira/Confluence
Regulatory awareness for UK banking context (DORA, FCA, PRA)
Preferred
Nice to Have
Banking/FinTech domain experience
Familiarity with agentic frameworks (LangChain, AutoGen, CrewAI)
Knowledge of MITRE ATLAS
Knowledge of OWASP Top 10 for LLMs
Customer-centric security design (minimizing UX disruption)
What you'll gain
More Than Just A Job.
We're committed to helping every team member grow professionally, personally and technically while working on meaningful projects.
Global Exposure
Collaborate with international clients and multicultural teams on enterprise programmes.
Continuous Learning
Expand your expertise through mentoring, certifications and hands-on project experience.
Career Growth
Take ownership, develop leadership skills and grow your consulting career over time.
Flexible Working
Hybrid and remote collaboration designed around trust and delivering exceptional outcomes.
People First
Join a supportive culture where collaboration, respect and long-term relationships come first.
Enterprise Projects
Work on meaningful technology initiatives for leading organisations across industries.
Apply
Apply for AI/ML Security Engineer (Agentic/LLM Guardrails) - Contract
One page, about two minutes. We only ask for what we actually need to have a first conversation.