AI Engineer Cybersecurity Platform (Full Stack / DevOps / LLM)

Company Description

We are building an enterprise-grade Automated Penetration Testing & Security Assessment Platform designed to help organizations continuously validate their security posture through AI-driven assessments, attack simulations, and automated reporting.

Our MVP is developed using a modern no-code foundation, and we are now scaling toward a cloud-native, highly scalable, production-ready architecture with AI-assisted capabilities.

We are looking for a highly skilled AI Engineer who can work across backend systems, AI integrations, DevOps, and scalable infrastructure to help transform the platform into a production-ready SaaS offering.

Role Description

The AI Engineer will be responsible for designing, developing, and deploying AI-powered features and scalable backend services for our cybersecurity platform.

This role requires strong expertise in: • LLM integrations • Backend engineering • Cloud-native architecture • DevOps automation • Security-focused environments (Docker/Kali containers)

You will work closely with product architects, security researchers, and frontend engineers.

Key Responsibilities

AI & LLM Engineering • Integrate external LLM APIs and deploy custom/self-hosted LLM models • Build AI agents for: • Automated pentest workflows • Security assessment reasoning • Report generation • Attack path analysis • Optimize prompts, latency, and cost efficiency • Implement RAG pipelines using vector databases • Build AI orchestration workflows

Backend & Platform Development • Develop scalable services using: • FastAPI • Node.js • TypeScript • Design REST and async APIs for platform modules • Implement job orchestration and task queues using Redis • Work with PostgreSQL (Supabase) data architecture

Cloud & DevOps • Design and manage containerized environments: • Docker • Kubernetes • Deploy scalable infrastructure on cloud platforms • Build CI/CD pipelines (GitHub Actions / GitLab / similar) • Optimize system performance, reliability, and observability

Security Platform Integration • Integrate containerized security tools (Kali Linux environments) • Build orchestration logic for automated security testing workflows • Implement secure multi-tenant architecture

Performance & Scalability • Design horizontally scalable architecture • Optimize system for large concurrent scans • Implement caching layers with Redis • Improve latency of AI and backend services

Required Technical Skills

Core Engineering • Strong experience with: • Python (FastAPI) • Node.js • TypeScript / JavaScript • Experience with React ecosystem (collaboration level)

AI / LLM • Experience integrating: • OpenAI / Anthropic / other LLM APIs • Experience with: • LangChain / LlamaIndex / agent frameworks • RAG pipelines • Prompt engineering • Fine-tuning or custom model deployment (preferred)

DevOps & Infrastructure • Docker & container orchestration • Kubernetes production deployments • CI/CD pipeline implementation • Redis (queues, caching) • PostgreSQL performance optimization

Cloud Platforms (Preferred) • AWS / GCP / Azure • Infrastructure as Code (Terraform preferred)

Preferred Experience (Highly Valuable)

• Cybersecurity or penetration testing domain knowledge • Experience with: • Security tools automation • Offensive security environments • SOC / detection / BAS platforms • Experience building SaaS products from MVP to scale • Multi-tenant architecture experience

Qualifications

• Bachelor’s or Master’s in Computer Science, AI, or related field • 3–7+ years experience in software engineering • 2+ years working with AI/LLM systems (preferred)

What Makes You a Great Fit

• You enjoy building complex systems from scratch • You are comfortable working in startup-style environments • You think about scalability, reliability, and architecture • You are passionate about cybersecurity and AI innovation

Nice to Have • Experience with vector databases • Knowledge of distributed systems • Experience with agentic AI frameworks • Knowledge of security compliance (ISO, SOC2)