Senior AI Security Engineer – Automated Pentesting & LLMs

SwiftCruit; United States; On-site; USD 145,000 - 250,000; Full time

Job summary

Synack is seeking a senior AI software engineer to design and ship AI agents for its PTaaS security lab. You will own systems end to end and help the team raise the technical bar.

You will build and scale production-grade AI-enabled security tooling with Go, Python, Docker, Kubernetes, and LLM agent frameworks, collaborating across teams to translate security research into reliable agent behavior.

Qualifications

• 7+ years of software engineering experience.
• Ability to build and scale production systems.
• Strong Python skills and polyglot codebase experience.
• Willingness to learn Go.
• Experience building LLMs and agentic frameworks (RAG, MCP).
• Creating reliable agents: prompting, evaluation, guardrails, cost optimization.
• Docker and Kubernetes with cloud experience (GCP preferred).
• Exposure to microservices, gRPC, API design, and async messaging (Pub/Sub, Kafka).
• Desire to understand how systems get compromised.
• Clear communication and collaboration across teams.

Responsibilities

• Build AI agents that automate penetration testing: planning, tool use, reasoning, and safe action.
• Stand up sandboxed cyber-lab and range infrastructure, containerised on Kubernetes.
• Ship features from ideation through production, including evals, guardrails and monitoring.
• Improve agent performance: prompting, tool orchestration, evaluation, and cost.
• Lead code reviews and design sessions, mentor engineers.
• Collaborate with security researchers to translate hacking methods into agent behavior.

Skills

Software engineering

Production systems

Python

Go

LLMs and agent frameworks

Agent prompting & guardrails

Docker & Kubernetes

Microservices testing

Security mindset

Communication

Collaboration

Tools

Docker

Kubernetes

gRPC

Pub/Sub

Kafka

Go

Python

Job description

Synack is seeking a senior AI software engineer to design and ship AI agents for its PTaaS security lab. You will own systems end to end and help the team raise the technical bar.

You will build and scale production-grade AI-enabled security tooling with Go, Python, Docker, Kubernetes, and LLM agent frameworks, collaborating across teams to translate security research into reliable agent behavior.