AI Engineer

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.

• 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)

Nice to have:

• Experience with fine-tuning LLM workflows
• Familiarity with MCP
• Experience with real time feature serving systems
• Exposure to graph-based retrieval and knowledge graphs

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