AI Engineer
Salary not listed • Bucharest • Full-time
Posted 1mo ago
Job Location
Bucharest
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
The opportunity is to build, test, and integrate production-grade AI agents and services that reliably execute business tasks within enterprise workflows. This role involves implementing agents, prompts, tools, retrieval pipelines, and orchestration logic, as well as integrating AI components with enterprise APIs, applications, databases, and workflow services. You will also build automated tests and evaluation datasets, diagnose failures in models, retrieval, and tool usage, and contribute to secure coding, documentation, peer reviews, and release activities.
Responsibilities
- Implement agents, prompts, tools, retrieval pipelines, and orchestration logic.
- Integrate AI components with enterprise APIs, applications, databases, and workflow services.
- Build automated tests and evaluation datasets for functional and non-functional behavior.
- Diagnose model, retrieval, tool-use, and integration failures.
- Contribute to secure coding, documentation, peer review, and release activities.
- Participate actively in agile ceremonies, demonstrations, and backlog refinement.
Requirements
- 3+ years in software, data, or AI engineering.
- Strong Python or comparable programming skills, API development, and version control.
- Practical experience with LLM applications, RAG, agents, embeddings, and structured outputs.
- Ability to work iteratively with product, architecture, data, and user-experience specialists.
- Hands-on experience building agents with at least one production-oriented framework (e.g., LangChain, LangGraph, Microsoft Agent Framework, Semantic Kernel, OpenAI Agents SDK, AutoGen, CrewAI).
- Strong Python skills and practical experience with FastAPI or similar API frameworks.
- Practical experience with Pydantic or comparable schema validation.
- Experience with asynchronous programming, Git, and automated testing.
- Practical experience implementing tool calling, structured outputs, agent state and memory, hand-offs, guardrails, retries, human-in-the-loop steps, and deterministic workflow nodes.
- Experience implementing RAG pipelines using embeddings, vector or hybrid search, metadata filters, reranking, and evaluation datasets.
- Familiarity with MCP, enterprise API integration, queues or events, containerization with Docker, and deployment to Kubernetes or managed application platforms.
- Ability to instrument agent executions using tracing and evaluation tools (e.g., LangSmith, MLflow, Langfuse, OpenTelemetry).