mazowieckie / Warszawa
Senior Agentic Engineer
2026-11-05
About the Project:
We are looking for a Senior Agentic Engineer to join a long-term project with our US-based client. The project involves developing and enhancing a modern SaaS platform in the healthcare technology domain. The platform supports medical practices in managing their operations and handling sensitive patient data.
You will work on both new product features and an established codebase, using AI agents as your primary development tool to deliver reliable, production-ready software. This is an opportunity to contribute to an innovative engineering workflow focused on end-to-end ownership, automated verification, and high-quality software delivery.
About the Role
We are looking for a Senior Agentic Engineer who uses AI agents as the primary tool for software development and takes full ownership of features from problem definition to production.
You will work across both new product functionality and a large, established codebase, building reliable software with AI-assisted workflows, strong testing practices, and a focus on measurable outcomes.
We value working software, code quality, and business impact over lines of code, pull request counts, or tokens consumed.
Senior Agentic Engineer
Miejsce pracy: Warszawa
Responsibilities
- Own features end to end: clarify requirements, define specifications and acceptance criteria, implement, test, deploy, and support features in production.
- Develop new product functionality and extend or refactor existing systems in a large, long-lived codebase.
- Use AI coding agents as your primary development workflow, including coordinating multiple agents in parallel.
- Build and maintain agent workflows, including context files, tests, hooks, and conventions that enable safe and effective work within an established codebase.
- Design automated tests and evaluation loops to verify AI-generated code and prevent regressions before human review.
- Identify edge cases, detect agent failures, and ensure implementation quality through systematic verification and incremental changes.
- Make sound technical and product decisions, prioritize work, reduce unnecessary complexity, and challenge requirements when a simpler solution can achieve the desired outcome.
- Document your development workflow and share best practices that other engineers can adopt.
Requirements
- 8+ years of experience building and operating production software, including senior or lead-level ownership of technical and product outcomes.
- At least 6 months of daily, agent-first development experience using tools such as Claude Code, Codex, Cursor Agent Mode, or similar solutions.
- Experience running multiple AI agents in parallel and integrating their output into reliable production software.
- A clear understanding of AI coding agents’ limitations and proven methods for managing risks through testing, evaluation, incremental changes, and code review.
- Strong experience working with large, established codebases, including refactoring, migrations, and legacy system constraints.
- Excellent testing practices and the ability to build verification systems that make AI-generated code trustworthy.
- Strong product judgment, including requirements clarification, specification writing, user-oriented problem solving, and scope management.
- Solid understanding of software security principles and experience working with sensitive data, such as health, financial, or personal information.
- Strong written English and the ability to create clear technical specifications for both AI agents and engineering teams.
- Experience with at least some of the following technologies: Python, Django, .NET, Angular, Kotlin, Swift, AWS, and SQL. Experience with adjacent technologies is also welcome.
- Availability for at least 4 hours of daily overlap with US Eastern Time.
Nice to Have
- Experience with healthcare software or other HIPAA-regulated SaaS products.
- Experience building multi-tenant B2B SaaS applications.
- Experience developing custom AI agent tooling, MCP servers, hooks, or evaluation harnesses.
- Experience leading incremental migrations from legacy platforms using the strangler-fig pattern.
- Side projects that you have built, maintained, and continue to use.
What We Value
- Ownership and accountability for outcomes, not just assigned tasks.
- An agent-first engineering mindset backed by evidence and measurable results.
- A strong focus on software quality, security, and reliability.
- The ability to simplify complex problems and deliver practical solutions.
- Clear communication, thoughtful technical decisions, and continuous improvement.
Interested?
If you enjoy building production-ready software with AI agents, solving complex engineering challenges, and taking ownership from idea to delivery, we would love to hear from you.
Apply now and join BekoreTech!
Apply now and join BekoreTech!