Generative AI Engineer

Job description

Key Responsibilities:

· Design, build, and maintain autonomous or semi-autonomous AI agents using frameworks such as LangGraph, Autogen, CrewAI, or Bedrock (Langgraph preferred)

· Engineer sophisticated prompting strategies to drive consistent, effective agent performance across dynamic use cases.

· Architect end-to-end solutions that integrate vector databases (e.g., Azure AI Search, FAISS, Pinecone) with real-time or batch ETL pipelines to power agent memory and retrieval-augmented generation (RAG).

· Leverage CosmosDB and other NoSQL data stores to manage large-scale, unstructured, and semi-structured data efficiently.

· Collaborate cross-functionally to integrate agent systems into broader products, APIs, and workflows.

· Continuously monitor the evolving GenAI landscape, evaluating new models, tools, protocols, and design patterns.

· Participate in code reviews, maintain code quality standards, and follow Git/GitHub workflows including branching, pull requests, and CI/CD practices.

· Conduct performance tuning and safety evaluations of AI agents across a variety of operational environments.

Prerequisites and skills

Required Qualifications:

· Strong programming skills in Python, including OOP principles and production-level code design.

· Demonstrated experience with prompt engineering techniques for large language models (LLMs) like GPT models, Claude, Gemini, or open-source equivalents.

· Deep understanding of AI agent concepts including memory management, planning, tool use, autonomous task execution, and evaluation metrics.

· Working knowledge of multi-agent orchestration frameworks, preferably LangGraph, but experience with Autogen, CrewAI, or similar is also valuable.

· Experience with vector databases (e.g., Azure AI Search, Pinecone, FAISS, Chroma) for embedding storage and semantic search.

· Understanding of ETL processes and data transformation pipelines in both batch and streaming architectures.

· Familiarity with NoSQL databases, specifically CosmosDB, and designing scalable schemas for AI-driven systems.

· Proficiency with Git/GitHub, including use of Gitflow or similar collaborative workflows.

· Demonstrated ability to stay current on the latest GenAI models, protocols (e.g., OpenAI Assistants, Function Calling, LangChain Agents), and research trend.

Preferred Qualifications:

· Experience deploying agents in cloud environments (Azure, AWS, or GCP).

· Familiarity with model fine-tuning, embeddings generation, and OpenAI plugin/tool calling.

· Exposure to observability and evaluation techniques for AI systems (e.g., human-in-the-loop, automated feedback loops).

· Plus - Contributions to open-source AI projects or publications in the field.

Further information

Seniority: Senior

Location: Remote

US Hours overlap needed (2-6 pm CET)?: 10am -6pm CET. possibility of a wider overlap (flexibility) appreciated

Language: EN

Start: ASAP

About the company

Technology and consulting software company.