AI Engineer

Twine builds AI Digital Employees who help cyber teams close the execution gap. Our first AI Digital Employee, Alex, learns, understands and takes away the burden of Identity and Access Management (IAM) tasks - proactively completing the organization's cyber objectives.

About the Role:

You’ll design, build, and ship the AI systems behind Alex: production agents that reason over customer identity data, call real tools, and complete IAM tasks end to end. Starting from a cybersecurity need, you’ll frame the technical problem, choose an approach, and own the solution through production: architecture, implementation, evaluation, deployment, and iteration on real customer behavior.

You’ll build on Twine’s shared agent infrastructure and extend it: new tools and integrations, workflow orchestration, context and memory management, evaluation harnesses, and the guardrails that keep an autonomous agent safe inside a customer’s environment.

This is a hands-on engineering role, not a research position. The goal is not to prove that an idea can work; it is to make it useful, reliable, and observable for customers in production.

What you'll do:

• Design, implement, and ship AI-powered features for complex cybersecurity workflows, from prototype to production.
• Build the systems that make agents work in practice: tool integrations, planning and orchestration logic, context management, structured outputs, and recovery from failures.
• Choose the right technical approach for each problem, combining models, deterministic logic, data, and conventional software where appropriate.
• Define quality for each use case and build the evaluation pipelines that measure correctness, task completion, consistency, safety, latency, and cost, and wire them into CI and release.
• Debug agent behavior in production: trace failures to their root cause in the prompt, tool, data, or architecture, and fix it.
• Own the reliability, observability, and cost of the agent systems you build.
• Collaborate with cybersecurity experts, product, and platform engineers throughout development.

Requirements:

• Excellent software engineering skills and substantial production experience with Python.
• Experience shipping and operating backend systems in production: APIs, async processing, data pipelines, testing, and observability.
• Hands-on experience building applications on modern language models: tool use, structured generation, retrieval, prompt and context management, and evaluation.
• Sound judgment about when to use an AI technique and when a deterministic approach is more effective.
• Comfort owning a problem end to end, from an ambiguous requirement to a system running reliably in production.

Nice to have:

• Building autonomous or long-running agents that interact with real systems.
• Building evaluation pipelines, simulations, or benchmarks for model behavior.
• Experience in cybersecurity, identity, security operations, or enterprise automation.
• Experience with agent frameworks, MCP, or LLM observability and tracing tools.