AI Platform Engineer

Role overview Help build and support enterprise AI applications such as chatbots, virtual assistants, analytics tools, and workflow automation. Working with guidance from experienced engineers, you’ll implement and test parts of retrieval-augmented generation (RAG) systems and connect language models with business data and applications in a governed environment.

Responsibilities - Implement and test components for embedding generation, vector indexing, document retrieval, context assembly, and language model responses. - Help integrate Azure OpenAI or similar services with APIs, data pipelines, reporting platforms, and enterprise applications. - Configure and evaluate vector search, including document chunking, metadata, and hybrid or semantic retrieval. - Add defined logging, error handling, monitoring, and usage tracking; document changes and test results. - Assist with deployments through established CI/CD pipelines and investigate routine issues, escalating complex cases. - Track usage and response performance, and help assess approved changes that may improve cost or reliability.

Requirements - Bachelor’s degree in computer science, engineering, or a related field, or equivalent practical experience; relevant internships and projects may count toward experience. - 2–4 years of relevant experience in software development, AI, platform work, or a related area. - Foundational Python skills and basic knowledge of backend development, REST APIs, and application integration. - Introductory understanding of large language models, prompt development, RAG, embeddings, and vector search. - Basic familiarity with cloud applications and Azure, plus awareness of usage-based model costs and performance monitoring. - Clear communication, attention to security and traceability, and willingness to learn, collaborate, and work from technical feedback.

Nice to have Exposure to .NET, Node.js, Azure OpenAI, Azure AI Search, or equivalent tools and services is useful.