Full Stack Engineer - Agentic AI

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:

We are looking for a strong Backend Engineer with 5+ years of experience to help build the core infrastructure behind Twine's agentic AI system. This is not another workflow tool: we are building something new, in a category that does not really exist yet. You will work on the services, orchestration, integrations, data models, retrieval layers, guardrails, and evaluation infrastructure that let AI agents reason over enterprise context and take reliable action.

This role is deeply product-facing and infrastructure-heavy. Our customers are large enterprises that manage tens of thousands of identities, so the systems we build need to be secure, observable, reliable, and able to operate at real scale.

What you'll do:

• Build production backend services in Python that power Twine's agentic AI platform.
• Design and implement AI-agent orchestration, tool-calling infrastructure, workflow execution, guardrails, and evaluation loops.
• Integrate with enterprise applications, identity providers, SaaS tools, and customer data sources so agents can understand context and execute tasks safely.
• Build systems that ingest, model, and reason over organizational processes, permissions, policies, and internal knowledge.
• Solve scale and reliability challenges for large enterprise environments with tens of thousands of identities.
• Collaborate closely with product, AI, and customer-facing teams to turn ambiguous business processes into reliable automated experiences.
• Own reliability, observability, performance, and security for production systems.

Requirements:

• 5+ years of professional backend engineering experience.
• Strong expertise in Python and production service development.
• Experience building complex, production-grade backend systems such as APIs, data pipelines, distributed systems, or workflow engines.
• Hands-on experience or strong practical familiarity with LLMs, agentic AI, tool calling, RAG, workflow orchestration, or AI infrastructure.
• Ability to design systems that use AI safely: validation, guardrails, evaluation, observability, and controlled execution.
• Solid understanding of databases, data modeling, and API design.
• Comfort working with ambiguous product requirements and turning them into robust technical designs.
• Excitement about building a new category and solving problems that do not have off-the-shelf answers.

Nice to have:

• Experience with identity, security, governance, permissions, or enterprise SaaS integrations.
• Experience with LLM evaluation, tracing, observability, or production AI systems.
• Experience building systems that automate complex operational workflows end-to-end.