Job Overview
Location
USA
Job Type
Full-time
Category
Software Engineering
Date Posted
February 28, 2026
Full Job Description
đź“‹ Description
- • Join a pioneering team at the forefront of offensive security innovation, tasked with building a fully autonomous AI pentesting agent from the ground up. This is a unique opportunity to shape the future of cybersecurity by developing a system capable of planning, exploiting, adapting, and reporting with unparalleled speed and precision.
- • As an AI Engineer, you will be instrumental in designing and implementing the core logic of this groundbreaking agent. Your focus will be on crafting sophisticated reasoning capabilities, robust memory systems, and efficient execution flows that enable the agent to tackle complex offensive security tasks with reliability and intelligence.
- • You will play a pivotal role in developing and optimizing the autonomous AI pentesting agent, with a strong emphasis on its fundamental logic and decision-making pathways. This involves translating abstract security concepts into concrete agent behaviors and functionalities.
- • Implement and refine the agent's core capabilities, including advanced reasoning mechanisms that allow it to understand and navigate complex attack vectors. Develop sophisticated planning algorithms that enable the agent to strategize and execute multi-step offensive operations.
- • Design and integrate effective tool orchestration, allowing the agent to seamlessly utilize a diverse range of security tools and scripts. Implement structured memory systems that enable the agent to retain context, learn from past actions, and adapt its strategies over time.
- • You will be responsible for building and maintaining secure, isolated environments specifically designed for the execution, testing, and benchmarking of the agent's behaviors. These environments will simulate realistic offensive security scenarios, allowing for rigorous evaluation of the agent's performance and effectiveness.
- • Contribute to the critical process of evaluating and comparing various Large Language Models (LLMs), including leading platforms like Claude, OpenAI, Mistral, and Llama. Your insights will directly influence the selection and fine-tuning of models to optimize specific agent tasks and enhance overall performance.
- • Develop user interface (UI) components and intuitive dashboards using React. These interfaces will be crucial for visualizing agent activity, monitoring performance metrics, and facilitating human oversight. Support browser automation workflows using Playwright, enabling efficient and scalable evaluation of the agent's capabilities across various web-based targets.
- • Actively support the continuous refinement and iterative improvement of the AI agent. This involves engaging in experimentation, establishing robust observability mechanisms to track agent actions and outcomes, and conducting rigorous testing within dedicated lab environments.
- • Collaborate closely with a team of experienced offensive security researchers. Your work will be guided by their expertise, ensuring that the agent's behaviors closely align with real-world attacker workflows, cutting-edge vulnerability exploitation methodologies, and the dynamic landscape of modern cybersecurity threats.
- • This role offers a high degree of autonomy and impact. You will be an early-stage member of a dedicated team, with significant ownership over technical decisions, system architecture, and the overall direction of the AI pentesting agent.
- • The position is full-time and remote, with a preference for candidates located in the UK or US. Compensation is competitive and includes a significant equity stake in this exciting AI venture.
- • You will be part of a rapidly scaling organization, working at the dynamic intersection of artificial intelligence and cybersecurity, offering unparalleled opportunities for professional growth and development.
- • The interview process is designed to be efficient and insightful, beginning with an introductory call with the founder and the AI agent team, followed by a technical evaluation and a discussion of your prior experience with AI agents.
🎯 Requirements
- • Minimum of 2 years of professional software development experience, with a high level of proficiency in Python.
- • Proven experience in building AI agents, leveraging frameworks such as LangChain, CrewAI, or similar Software Development Kits (SDKs).
- • Hands-on experience with core AI agent design principles, including reasoning patterns, effective tool orchestration, robust memory management, and the generation of structured outputs.
- • Proficiency in advanced Large Language Model (LLM) techniques such as prompt engineering, Retrieval-Augmented Generation (RAG), chain-of-thought processing, and few-shot learning.
- • Experience with a technical stack including SQL/NoSQL databases, data modeling, Docker, AWS, cloud deployment, and shell scripting.
- • Experience using React for developing frontends and analytical dashboards.
- • A demonstrable interest in cybersecurity; while deep expertise is not a prerequisite, strong curiosity and a passion for the field are essential.
🏖️ Benefits
- • Competitive compensation package, reflecting your skills and experience.
- • Significant equity stake in the AI pentesting venture, offering ownership and upside potential.
- • High degree of autonomy in an early-stage role, with substantial ownership over technical decisions and system architecture.
- • Opportunity to work at the cutting edge of AI and cybersecurity within a fast-growing organization.
Skills & Technologies
Python
React
AWS
Docker
Data Science
Remote
About MLabs
MLabs is a technology company specializing in the development and implementation of advanced laboratory automation solutions. They focus on creating intelligent systems that streamline complex laboratory workflows, enhance data accuracy, and improve overall efficiency for research and development, quality control, and clinical diagnostics. Their offerings often include robotics, AI-driven software, and integrated hardware designed to automate tasks such as sample handling, analysis, and reporting. MLabs serves a diverse range of industries including pharmaceuticals, biotechnology, and healthcare, aiming to accelerate scientific discovery and improve patient outcomes through cutting-edge automation.
