Software Engineer II | AI & Agentic Systems

Role

You will be a Software Engineer II on a greenfield team building production systems that allow AI agents to perform real work on real code within deterministic gates, with independent verification and a full audit trail. The work sits at the intersection of software engineering and security, starting within the Security domain of an established platform.

Key Responsibilities

• Build production systems where AI agents author changes that execute inside deterministic gates and produce auditable evidence.
• Break customer and platform problems into implementable pieces and own them end-to-end with an agile team.
• Design trust boundaries, blast radius limits, and least-privilege models for automation that may hold elevated access to production.
• Implement evaluation and observability to detect accuracy drift and silent degradation in non-deterministic systems.
• Produce verifiable evidence for auditors that controls worked as intended.
• Collaborate closely with security engineering and product/dev teams and communicate complex trade-offs clearly.
• Apply engineering best practices, mentor peers, and drive high-quality delivery.

Requirements

Must-have:

• 3+ years building enterprise-grade software commercially, with strong testing and QA practices.
• 3+ years of commercial experience in Java or Python.
• Hands-on experience building with LLM APIs and agentic frameworks (tool calling, multi-step execution, structured output), beyond using AI coding assistants.
• Hands-on experience using AI-driven coding assistants (e.g., GitHub Copilot, Cursor, Claude Code) to accelerate development.
• Sound judgment on where automation should and shouldn’t act autonomously; ability to articulate those boundaries.
• A mindset oriented to trust boundaries, blast radius, and least privilege.
• Discipline in vulnerability management (severity, exploitability, SLAs, exception handling).
• Experience working in agile teams and familiarity with build systems such as Jenkins or Bamboo.
• Strong collaboration and communication skills and ability to work in a fast-paced environment.

Nice-to-have

• Software supply chain security experience (SBOMs, provenance and attestation, image signing/verification, policy-as-code).
• Experience running AI coding agents at repository scale and building harnesses to make their output trustworthy.
• Familiarity with AI governance in security contexts (model-use policy, data handling, auditability for agent-initiated changes).
• Experience in regulated environments (SOC 2, FedRAMP, or similar) and understanding of auditor expectations.

Location & Remote

This role is offered remote for candidates based in Poland or those who have sponsorship to live and work in Poland. Occasional in-person attendance at local Jamf offices or collaborative work locations may be required for certain events.

Benefits

• 30 days paid time off
• 3 paid volunteer days per year
• Multisport Card
• Luxmed healthcare packages
• Remote work (Poland-based)