Senior Agentic Software Engineer | Remote Romania

You will work on enterprise software modernization projects, using advanced AI coding tools such as Claude Code, Cursor and Codex to accelerate development, improve code quality and solve complex engineering challenges.

This role is ideal for an experienced software developer who actively uses AI agents in their daily development workflow and understands how to guide, validate and optimize their output.

Key Responsibilities

• Work with AI-powered coding agents to support and accelerate software modernization initiatives.

• Configure, customize and optimize prompts to achieve reliable and high-quality results.

• Launch modernization tools and validate their outputs.

• Investigate, troubleshoot and resolve issues related to AI-generated code and prompts.

• Review AI-generated code critically, identifying errors, inconsistencies and potential risks.

• Collaborate with engineering and modernization teams to deliver solutions aligned with project objectives.

• Take ownership of technical challenges, from initial investigation through implementation and production.

• 5+ years of professional software development experience, preferably as a Full Stack Engineer.

• Daily hands-on experience using AI coding agents such as Claude Code, Cursor, Codex or similar tools as part of your development workflow.

• Good understanding of LLM agents, including context management, tools, planning, subagents and common failure modes.

• Strong ability to review, validate and debug AI-generated code.

• Experience with relational databases, SQL and familiarity with graph databases (Neo4j) and vector databases.

• Hands-on experience with Docker, Kubernetes and Helm.

• Knowledge of unit and integration testing, TDD and tools such as Testcontainers.

• Ability to work independently, make technical decisions and take ownership of solutions.

• English proficiency at B2 level or higher.

Nice to Have

• Experience with LLM APIs such as OpenAI, Anthropic or AWS Bedrock, or gateways such as LiteLLM.

• Experience with R&D, prototyping and experimentation.

• Mainframe knowledge, including COBOL, CICS, JCL, DB2 or IMS.

• Experience building evaluation frameworks for AI-generated outputs and non-deterministic systems.

• Knowledge of AI agent security, prompt injection, data leakage and OWASP Agentic AI security risks.