Software Engineer, AI Engineering, Consulting
Summary
The Software Engineer for AI Engineering is responsible for the design, development, and deployment of an autonomous penetration testing platform that leverages Large Language Models (LLMs) and AI agents to enhance automated offensive security capabilities.
This role involves building production-grade services that support both staging and production environments. The incumbent will collaborate closely with AI researchers, cybersecurity specialists, and DevOps engineers to deliver a secure, scalable, and reliable platform supporting continuous penetration testing operations.
Duties and Responsibilities
- Design and implement backend microservices in languages such as Python and Go for orchestrating autonomous agents and workflow automation.
- Develop frontend interfaces and dashboards using languages and frameworks such as TypeScript, React, Next.js, and Tailwind CSS to manage, visualise, and report testing activities.
- Ensure system scalability, performance, and maintainability through robust architecture, modular design, and efficient code practices
- Integrate LLM-based automation and reasoning components into penetration testing workflows
- Develop prompt orchestration, model chaining, and contextual reasoning capabilities for AI agents
- Work with AI researchers to translate prototype logic into production-ready components and APIs
- Incorporate AI security considerations into design and development of AI agents, MCP tools and other APIs
- Support secure operation of the AI platform through logging, monitoring, and sandbox isolation mechanisms
- Adhere to best practices for software development lifecycle (SDLC) standards and documentation requirements
- Ensure code quality through automated testing, code reviews, and version control practices
- Comply with cybersecurity and data protection requirements in all development activities
Requirements
- Minimum 2+ years of professional experience in full-stack or backend software engineering roles
- Backend Development experience with Python, Golang, or other similar languages.
- Experience with frontend frameworks (React, Next.js) and languages (TypeScript, CSS).
- Proficiency with Linux environments and command-line tools.
- Strong analytical thinking and exceptional attention to details.
- Understanding of offensive security, penetration testing methodologies, or cybersecurity frameworks such as MITRE ATT&CK or OWASP
Nice to Haves
- Experience with AI development tools such as Cursor, GitHub Copilot, or Claude.
- Hands-on experience integrating and deploying AI applications using foundation model APIs and inference services, including OpenAI, Anthropic, and local/self-hosted LLM providers.
- Demonstrated experience deploying applications to production environments (with Docker / Kubernetes), and modern CI/CD pipelines.
- Familiarity with cloud platforms (AWS, GCP, or Azure) and database systems (PostgreSQL, MySQL, etc)
- Exposure to AI agent frameworks (Agno, Claude Agent SDK), LLM orchestration, or prompt engineering
- Experience in event-driven architecture or distributed systems
- Knowledge of secure coding practices and DevSecOps principles
- Prior work in cybersecurity, AI or adjacent domains.