Responsibilities

:Lead development of the Patch Backporter library:Design and evolve its architecture and abstractions.Keep it clean, composable, and extendable for new models and techniques.Design and lead major changes in patch backporting automation:Identify bottlenecks and weak points in current workflows.Propose and drive cross-component improvements end-to-end.Own and evolve benchmarking and evaluation infrastructure:Design metrics, datasets, and evaluation flows to measure backporter performance.Automate benchmarks in CI and make results stable and comparable over time.Integrate improvements into the existing automation stack:Plan and implement how backporter updates propagate into the broader automation ecosystem.Work with CI/CD, services, and databases so changes are fully wired into production.Accelerate iteration within the team:Build Python tools, CLIs, small services, and helpers that make experiments faster and cheaper.Improve local dev setups, test harnesses, and engineering processes for research.Collaborate and communicate:Work cross-functionally with other engineering teams to align on interfaces and integration points.Write clear technical documentation, design docs, and experiment logs.Mentor junior engineers and share knowledge on AI, infra, and tooling.

Requirements

To be successful, you should have:

Education & ExperienceBSc or MSc in Computer Science, Engineering, or a related field.5+ years in software engineering as a developer, tech lead, or team lead.Demonstrated ownership of complex systems or components (not just small features).AI & LLMsHands-on experience integrating LLMs in real projects (OpenAI, Anthropic, etc.).Familiarity with common approaches such as RAG, CAG, agents, tool-calling, etc.Software EngineeringStrong Python skills (mandatory), including:Asyncio / multithreading / multiprocessing concepts and usage.Testing frameworks (pytest, unittest) and a solid testing culture.Experience with database design and querying:PostgreSQL or another SQL database.MongoDB or another NoSQL database.Infrastructure & ToolingExperience with CI/CD tooling (Jenkins, GitLab CI, or similar), test automation, and containerization (Docker).Confident Linux CLI user.Experience supporting or operating services on Linux/Unix VMs.Willingness and desire to use AI development tools (e.g., Cursor) in day-to-day work.Ways of WorkingAbility to take loosely defined problem statements and turn them into concrete plans (architecture, milestones, experiment design) with minimal supervision.Strong written communication skills in English (design docs, experiment logs, clear merge requests).

It is a plus if you also have:

Published research or documented experimentation experience in any Computer Science topic.Experience formulating and testing hypotheses (e.g., comparing models, algorithms, or system designs).Data analysis skills:Representing results via tables, plots, or dashboards.Designing meaningful metrics for system performance and quality.Basic knowledge of the C language (able to read patches, understand diffs and build issues).Regular usage of AI engineering tools (Cursor, WindSurf, aider, Claude Code, etc.).

Benefits

What's in it for you?

A strong focus on professional development with opportunities for learning and growth:Interesting and challenging projects,Mentor and other knowledge-exchange programs;Fully remote work with flexible working hours, that allows you to schedule your day and work from any location worldwide;Paid 24 days of vacation per year, 10 days of national holidays, and unlimited sick leaves to ensure you maintain a healthy work-life balance;Compensation for private medical insurance;Co-working and gym/sports reimbursement;The opportunity to receive a reward for the most innovative idea that the company can patent, fostering a culture of creativity and innovation.

By applying for this position, you consent to the processing of your personal data as described in our Privacy Policy ( ), which provides detailed information on how we maintain and handle your data.