# Smart Hob

Smart Hob is a remote worker on Himalayas, Lead Security Consultant at Halvsec, based in United Kingdom.

Source: https://himalayas.app/@smarthob

```text
I lead offensive AI security—building and breaking LLM/agent systems with product-grade workflows.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | United Kingdom |
| Authorized to work in | United Kingdom |
| Job categories | Offensive Security Director, Offensive Security Consulting, AI Security Consultant, AI Security Engineer, Blockchain Security Engineer, Product Security Engineer, Offensive Security Leadership, Offensive Security Engineer, Director Of Offensive Security Research |
| Skills | AI Red Teaming, Jailbreaking, Tool Abuse, Workflow Agents, Adversarial Testing, Multimodal Attack Design, Threat Led Offensive Testing, Security Architecture Review, Exploit Development, API Testing, Cloud Security, Incident Response, Digital Forensics, Security Engineering, GuardRails, Open Source Security, Copilot Security Review, OSWE, GWAPT, Blockchain, Run.Ai, Toolkit |

## What I'm looking for

```text
I’m looking for teams that value judgment, speed, and depth over theatre—where offensive AI security meets product-grade delivery. I want to build scalable operator workflows and governance-driven tooling like SMART for real deployments.
```

## About

```text
I’m an OffensiveSecurityLead and Lead Security Consultant/Managing Director focused on AI redteaming, jailbreaks, prompt injection, tool abuse, and agent security. Over the last 10 years, I’ve worked across offensive security, adversarial AI, blockchain security, incident workflow/security response, and security product engineering—turning deep technical testing into usable product and consulting value.

My strongest work happens where “deep technical testing and product judgment need to meet.” I build operational security platforms like SMART (a multi-tenant AI redteam toolkit) and lead engagements spanning applications, APIs, cloud, infrastructure, and blockchain environments. I translate findings into decision-useful reports, governance/guardrails, and repeatable operator workflows—staying hands-on in architecture review, exploit design, tooling, and delivery.
```

## Experience

### Lead Security Consultant (current)

Halvsec. Jan 2023 - Present

```text
Led AI security, offensive security, and blockchain security engagements, including architecture reviews and offensive testing for LLM and agent workflows. Managed a technical team while translating findings into reports and recommendations for engineering and leadership.
```

Skills: LLM-Security, Threat-Led-Offensive-Testing, Prompt-Injection-Mitigation, Incident-Response-And-Forensics, Security-Architecture-Review

### AI Security Contractor

Arm. Jan 2025 - Apr 2026

```text
Advised on enterprise AI deployments and AI-assisted workflows for security, governance, and operational fit through security writing and security-focused reviews of copilots and connected LLM usage. Converted technical AI security findings into decision-ready materials for program and leadership stakeholders.
```

Skills: Security-Reviews, Copilot-And-Developer-Tooling-Assessment, Prompt-And-Workflow-Governance, Blockchain-Security-Abuse-Paths, Access-Drift-Analysis, Security-Writing

### Lead Offensive Security Eng

Hacken. Jan 2023 - Jan 2025

```text
Performed offensive security audits across Web2, Web2.5, Web3, and AI-connected developer systems while contributing to a client security portfolio. Recognized as a department revenue leader for delivery and book contributions.
```

Skills: Web3-Security, AI-Connected-System-Testing, Reverse-Engineering

### AI Security Podcast & Consulting

Independent Consulting. Jan 2017 - Jan 2023

```text
Built depth across penetration testing, red teaming, reverse engineering, incident response/forensics, and blockchain security through independent consulting work. Helped introduce new security capabilities, including blockchain security services and custom security tooling.
```

Skills: Penetration-Testing, Red-Teaming, Reverse-Engineering, Incident-Response, Forensics, Blockchain-Security, Security-Consulting, Threat-Assessment

## Tech stack

- Blockchain
- Gmail
- Toolkit
- GuardRails
- Run:AI
- Make
- Remote

To contact Smart, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Matt Fieldhouse](https://himalayas.app/@mattfieldhouse): Director of Security and Compliance, Zipline
- [Jack Griffiths](https://himalayas.app/@jackgriffiths1): Managing Security Consultant, Bastion Security Group
- [Daniel Kaye](https://himalayas.app/@danielkaye): Cybersecurity Developer, Researcher, and Consultant, Unnamed Israeli Security Startup
- [Sunny Razario](https://himalayas.app/@sunnyrazario): Cyber Security Consultant, Capgemini
- [Jakub Kaczmarczyk](https://himalayas.app/@jakubkaczmarczyk): Senior Penetration Tester, Confidential
- [Marcel Clarembaux](https://himalayas.app/@marcelclarembaux): Freelance Blockchain Security Researcher, Independent
- [Adeola Mercy](https://himalayas.app/@adeolamercy): Azure Cloud Engineer, Bank of England
- [Anton Sidorov](https://himalayas.app/@antonsidorov): OpenAI Safety Bounty Research, OpenAI Safety Bounty
- [Aamer Shareef](https://himalayas.app/@aamershareef): Senior Cyber Security Engineer, Veson Nautical
- [Shantanu Shastri](https://himalayas.app/@shantanushastri): Founder & Lead Organiser, BSides Eastbourne
