AI Engineer

About the company

Autopay Global is the newest member of the Autopay family, aiming to expand the reach of the group’s state-of-the-art payment integration and payment data technologies to the international market, providing seamless integration with local PSPs, support for multiple currencies and compliance with local frameworks. We have a very forward-looking approach to our products, we value creativity, passion and drive to leverage the newest achievements in technology to our advantage.

To support our dynamic expansion, we are looking for a new AI Engineer for a full-time,

About the role

The AI Engineer is a core builder within Autopay’s Data & AI Platform, responsible for designing, implementing, and operating the AI-ready infrastructure that powers personalization, retrieval, and agent-based decisioning. This role bridges advanced ML/AI research and production-grade data engineering, ensuring Autopay’s AI Core runs on robust, well-governed, and performant data pipelines.

As an AI Engineer, you will:

•         Design and implement RAG pipelines: document ingestion, chunking, embedding generation, retrieval evaluation, and index refresh strategies,
•        develop and maintain RAFT workflows: produce high-quality supervised datasets with provenance, instruction-style examples, and clear labeling guidelines for retrieval-aware fine-tuning,
•        build MCP-based agent data tools,
•        integrate with Google Vertex AI,
•        maintain and optimize the real-time feature layer,
•        build hybrid retrieval + reranking pipelines,
•        collaborate with Data Engineers on embedding and feature data products,
•        partner with the Data Science team on model evaluation,
•        contribute to data governance for AI: schema contracts for embeddings, versioning policies for training datasets, lineage for model inputs, and PII handling in AI pipelines.

What tools will you be working with?

• Technology: Google Vertex AI, Databricks, Delta Lake, Vertex AI Vector Search, GCS, Kafka
• Nice to have: Experience with fine-tuning LLM workflows, familiarity with MCP, experoence with real time feature serving systems, exposure to graph-based retrieval and knowledge graphs. 

Requirements and skills we are looking for in a person hired for this role:

•       5+ years in AI/ML engineering with production deployment experience; strong software engineering foundations.
•       hands-on experience building and operating RAG systems: document ingestion, chunking, embedding generation, vector indexing, and retrieval evaluation,
•       experience with retrieval-aware training approaches (e.g., RAFT or equivalent) and producing high-quality supervised datasets with provenance,
•      Google Vertex AI experience: training pipelines, inference endpoints, dataset management, model registry, and evaluation workflows, 
•      strong Python skills; experience with PySpark, Databricks, or equivalent distributed processing frameworks,
•      understanding of vector databases, embedding models, and hybrid search (dense + sparse retrieval, reranking),
•      ability to design and implement tool APIs for agent systems with strict access controls and audit logging (MCP or similar protocols).

What we are offer?

• being a part of a fast-growing, global fintech company, 
• possibility to work with cutting-edge tools and technologies,
• independence in decision-making,
• friendly working environment, team support, no dress code. 

Join us and let's head together where no one has gone before!