Job Description
AI Engineer
Role Summary
VE3’s AI Engineer will help design and implement AI-enabled capabilities that improve how data and APIs are structured, discovered, and consumed. The role will focus on applying practical AI and machine learning techniques to support search enhancement, metadata enrichment, semantic discovery, and future-ready data services. The AI Engineer will work closely with API, data, and platform specialists to ensure AI components are usable, governed, secure, and integrated into production-grade services.
Requirements
Key Responsibilities
* Design and implement AI-enabled components to improve discoverability, relevance, and usability of data and API services.
* Develop approaches for metadata enrichment, semantic tagging, classification, and intelligent search optimisation.
* Support the design of hybrid search patterns combining keyword, vector, and semantic retrieval methods.
* Build and test AI pipelines, embeddings workflows, retrieval mechanisms, and prompt-driven enrichment processes where required.
* Work with structured and unstructured data to improve search quality and machine-readability.
* Evaluate model performance, relevance, bias, and operational suitability using measurable quality criteria.
* Collaborate with architects and developers to integrate AI capabilities into scalable production services.
* Support governance, traceability, and responsible AI controls across design and implementation.
* Document AI models, assumptions, configurations, and operational guidance for supportability and knowledge transfer.
Skills & Experience
* Strong experience in applied AI/ML engineering, particularly in search, NLP, embeddings, or information retrieval.
* Experience with Python and common AI/ML tooling and frameworks.
* Understanding of vector search, semantic retrieval, RAG patterns, metadata enrichment, and search relevance tuning.
* Experience integrating AI capabilities with APIs, data platforms, and cloud environments.
* Ability to work with data quality, model evaluation, and responsible AI considerations.
* Strong analytical and problem-solving capability.
Desirable
* Experience with hybrid search platforms, knowledge graphs, or ontology-driven metadata models.
* Familiarity with OpenAPI-linked AI use cases, agentic workflows, or AI-assisted developer tooling.
* Experience with model monitoring, prompt controls, and human-in-the-loop assurance.
Requirements
Key Responsibilities Design and implement AI-enabled components to improve discoverability, relevance, and usability of data and API services. Develop approaches for metadata enrichment, semantic tagging, classification, and intelligent search optimisation. Support the design of hybrid search patterns combining keyword, vector, and semantic retrieval methods. Build and test AI pipelines, embeddings workflows, retrieval mechanisms, and prompt-driven enrichment processes where required. Work with structured and unstructured data to improve search quality and machine-readability. Evaluate model performance, relevance, bias, and operational suitability using measurable quality criteria. Collaborate with architects and developers to integrate AI capabilities into scalable production services. Support governance, traceability, and responsible AI controls across design and implementation. Document AI models, assumptions, configurations, and operational guidance for supportability and knowledge transfer. Skills & Experience Strong experience in applied AI/ML engineering, particularly in search, NLP, embeddings, or information retrieval. Experience with Python and common AI/ML tooling and frameworks. Understanding of vector search, semantic retrieval, RAG patterns, metadata enrichment, and search relevance tuning. Experience integrating AI capabilities with APIs, data platforms, and cloud environments. Ability to work with data quality, model evaluation, and responsible AI considerations. Strong analytical and problem-solving capability. Desirable Experience with hybrid search platforms, knowledge graphs, or ontology-driven metadata models. Familiarity with OpenAPI-linked AI use cases, agentic workflows, or AI-assisted developer tooling. Experience with model monitoring, prompt controls, and human-in-the-loop assurance.