Mission
Industrialize AI-assisted engineering workflows for Meridian by packaging repeatable patterns that support codebase intake, dependency extraction, build triage, documentation generation, and technical evidence creation across cloud software work packages.
Role focus
This position emphasizes reusable workflow engineering. The candidate should combine Python, APIs, orchestration frameworks, retrieval patterns, and AI development platforms to create governed workflows that can be reused across repositories, OpenStack-derived services, CI/CD outputs, architecture documentation, and handover evidence.
Key responsibilities
Build reusable AI-assisted workflows for repository analysis, code scanning, service decomposition, dependency discovery, build diagnosis, and documentation generation.
Package prompts, tools, retrieval layers, model routing, evaluation checks, retries, and human approval steps into repeatable engineering accelerators.
Integrate AI workflows with Git platforms, CI/CD systems, documentation stores, issue trackers, test outputs, service catalogues, and architecture evidence repositories.
Create workflow outputs that remain auditable, including traceable source references, confidence indicators, reviewer checkpoints, and explicit assumptions.
Experiment with open-source, open-weight, and Chinese coding models in approved environments to compare usefulness for SDLC automation and handover tasks.
Support work-package leads by translating ambiguous engineering questions into structured AI-assisted workflows and validated deliverables.
Examples of market tools, models, and SDLC platforms expected
Agentic workflow frameworks such as LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, LlamaIndex Workflows, Semantic Kernel, or comparable orchestration stacks.
AI development platforms and editor integrations such as Cursor, Windsurf, Claude Code, Continue, Cline, Aider, or VS Code-compatible internal assistants.
Model families relevant to SDLC automation such as DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or enterprise-hosted frontier models.
Supporting components including vector databases, graph stores, code indexing, OpenAPI wrappers, GitLab/GitHub APIs, Jenkins APIs, observability, and evaluation dashboards.
Candidate profile
5+ years of engineering experience across software development, DevOps automation, platform engineering, or AI workflow implementation.
Strong hands-on Python skills, API integration experience, and practical knowledge of orchestration frameworks, RAG patterns, tool calling, and evaluation loops.
Experience turning prototypes into reusable engineering workflows with clear interfaces, logging, error handling, configuration, and maintainability discipline.
Good understanding of CI/CD, Git workflows, containers, Kubernetes, software architecture documentation, and modular cloud software environments.
Strong written communication skills for creating workflow documentation, evidence packs, usage guidance, and decision support for senior stakeholders.
Comfortable operating in ambiguous, confidentiality-sensitive settings where AI outputs must be reviewed, justified, and converted into reliable engineering evidence.
Please note: remote working is only possible from within Hungary due to European taxation regulations.
* Please be informed that our remote working possibility is only available within Hungary due to European taxation regulation.