Agentic AI Security Specialist

HCL Technologies Limited; Greater London; Hybrid; GBP 120,000 - 170,000; Full time

Job summary

HCL Technologies Limited in London is seeking an Agentic AI Security Specialist to secure autonomous multi-agent AI ecosystems within a highly regulated banking environment.

You will design secure architectures, perform threat modeling, and engineer detection metrics to ensure compliant operations of agentic systems under UK banking regulations.

Qualifications

• 5+ years of dedicated professional experience in Cyber Security Engineering, Security Architecture, Detection Engineering, or DevSecOps in highly regulated environments (ideally Banking/FinTech).
• 2+ years focusing explicitly on AI/ML Security, covering LLM guardrails, adversarial machine learning, or security engineering for automated execution pipelines.
• Experience designing secure architectures for autonomous multi-agent systems and enforcing least privilege.

Responsibilities

• Perform specialized Threat Modeling on multi-agent orchestrations, focusing on tool-use vulnerabilities and autonomous execution manipulation.
• Architect secure execution environments and sandboxes to isolate autonomous agents and enforce least privilege.
• Implement real-time proxy guardrails and Advanced Threat Protection boundaries to intercept malicious prompts and data exfiltration vectors.

Skills

Cyber Security

AI Security

Security Architecture

Threat Modeling

Offensive Security Testing

Python

Go

DevSecOps

Jira

Confluence

Tools

LangChain

AutoGen

CrewAI

Job description

HCLTech is a global technology company, home to 219,000+ people across 54 countries, delivering industry-leading capabilities centered on digital, engineering and cloud, powered by a broad portfolio of technology services and products. We work with clients across all major verticals, providing industry solutions for Financial Services, Manufacturing, Life Sciences and Healthcare, Technology and Services, Telecom and Media, Retail and CPG, and Public Services. Consolidated revenues as of $13+ billion.

For more information on how we process your personal data, please refer to HCLTech's Candidate Data Privacy Notice.

Job Title: Agentic AI Security Specialist

Role Overview

As an Agentic AI Security Specialist, you will secure the bank’s autonomous, multi-agent AI ecosystems. Unlike static machine learning models, agentic systems possess tool-use capabilities, multi-step planning, and execution autonomy, introducing complex security boundaries.

You will design secure architectures, perform specialized threat modeling, conduct offensive security testing, and engineer advanced detection metrics to ensure autonomous agents operate safely within strict UK banking regulations.

• Location: London, UK (Hybrid)
• Sector: Highly Regulated Financial Services / Banking
• Experience Level: Senior / Specialist

Experience & Background Requirements

• Cyber Security Foundations: 5+ years of dedicated professional experience in Cyber Security Engineering, Security Architecture, Detection Engineering, or DevSecOps within highly regulated environments (ideally Banking/FinTech).
• AI Security Domain: 2+ years of hands‑on experience focusing explicitly on AI/ML Security, covering LLM guardrails, adversarial machine learning, or security engineering for automated execution pipelines.

Skill Matrix Overview

Core Domain

Primary Skills (Critical for Day 1)

Secondary Skills (Supportive & Operational)

Security Architecture

• Security Engineering

Threat Management

• Detection Engineering
• Offensive Security Testing

Engineering & Strategy

Primary Roles & Responsibilities

1. Agentic Threat Modeling & Secure Engineering

• Perform specialized Threat Modeling on multi-agent orchestrations, focusing on tool-use vulnerabilities, autonomous execution manipulation, goal-jacking, and cascading agent failures.
• Architect secure execution environments (Security Engineering) and sandboxes to isolate autonomous agents, ensuring strict enforcement of the principle of least privilege.
• Implement real-time proxy guardrails and Advanced Threat Protection boundaries to intercept malicious prompts, indirect prompt injections, and data exfiltration vectors.

2. Offensive Simulation & Detection Engineering

• Execute Offensive Security Testing specifically mimicking adversarial machine learning tactics against agent reasoning loops, vector databases, and memory layers.
• Design custom Detection Engineering logic to identify anomalous agent behaviors, API misuses, and malicious intent vectors before downstream execution occurs.
• Develop automated orchestration pathways (Response Engineering) to instantly isolate, throttle, or terminate rogue agent threads without disrupting core systems.

3. Core Language & Automation Engineering

• Write production-grade security proxies, wrapper interfaces, and low‑latency validation controls using Python and the Go Programming Language.

Secondary Roles & Responsibilities

• Conduct proactive Cyber Threat Hunting exercises to uncover hidden signs of systemic poisoning, persistent agent manipulation, or silent model exploitation.
• Perform advanced Digital Forensics on complex agent memory logs, tracking step-by-step reasoning patterns and API execution loops following anomalous events.

2. Governance, Delivery, & Enablement

• Embed security guardrails smoothly into production deployment loops using DevOps pipelines (CI/CD) and automated testing frameworks.
• Operate within high-velocity teams using Agile Methodology & Tools (e.g., Jira, Confluence) to cleanly deliver tasks inside sprint timelines.
• Maintain a mindset of Customer Centricity, ensuring that heavy security layers and model guardrails do not negatively disrupt the user experience.
• 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).

Regulatory Context

Architectures must be engineered to comply natively with stringent UK and international banking regulations, including:

• DORA (Digital Operational Resilience Act): Ensuring operational resilience of autonomous systems under stress.
• FCA & PRA Guidelines: Adhering to strict compliance for automated decision-making pipelines and accountability frameworks.