AI Data Engineer III

Boston Scientific•Arden Hills, MN

7h•$82,100 - $156,000•Hybrid

About The Position

Boston Scientific was recognized by Forbes as one of the Best Workplaces for Engineers in 2026, reflecting a culture where engineers do meaningful work. Boston Scientific was recognized as a Glassdoor Best Place to Work in 2026, ranking No. 15 on the Top 100 list, reflecting the culture our employees experience every day. We are seeking an AI Data Engineer III to join our AI Engineering team and design, build and operate the data foundations that power enterprise AI products. In this hands-on role, you will develop scalable data platforms and pipelines for retrieval-augmented generation (RAG), enterprise search, document intelligence and knowledge-driven applications. The incumbent will own complex data engineering components from design through production, including unstructured content processing, search and vector indexing, large language model (LLM)-based enrichment, graph data and application-facing APIs. You will partner with AI engineers, solution architects, software engineers, data scientists and business stakeholders to deliver secure, observable and cost-effective solutions in a regulated enterprise environment.

Requirements

Bachelor's degree in computer science, software engineering, data engineering, information systems or a related technical field, or equivalent practical experience.
Minimum of 3 years' experience in data engineering, software engineering or AI/machine learning engineering, including experience delivering production data pipelines or services.
Hands-on experience with Python and SQL and software engineering practices such as version control, automated testing, code review and continuous integration and delivery.
Experience building cloud-based data pipelines and services using AWS and/or Microsoft Azure.
Experience designing or consuming APIs and integrating data services with downstream applications.
Understanding of data modeling, data quality, lineage, logging and observability.
Proven ability to communicate technical concepts clearly, collaborate across disciplines and independently own engineering work through production and ongoing operations.

Nice To Haves

Experience with AWS Bedrock and related AWS services for generative AI, document processing, enterprise search, orchestration and monitoring.
Experience with enterprise search, RAG and vector databases, including embeddings, chunking, index design, hybrid retrieval, migration, tuning and retrieval evaluation.
Experience with graph databases, knowledge graphs or graph-enhanced retrieval, as well as conversational AI or agentic frameworks such as LangGraph, Semantic Kernel or similar technologies.
Experience evaluating and operationalizing generative AI solutions using relevance, groundedness, answer quality, latency, cost and safety metrics, with familiarity in infrastructure as code, containerization, orchestration, MLOps or LLMOps.
Experience with product lifecycle management platforms such as Windchill, highly regulated industries such as health care, life sciences or medical devices, and mentoring engineers or contributing to reusable technical standards and platform capabilities.

Responsibilities

Design, build and operate scalable AI data platforms supporting RAG, enterprise search, document intelligence, knowledge graphs and knowledge-driven applications.
Develop production-grade pipelines to ingest, parse, normalize, chunk and enrich structured and unstructured enterprise content, including technical and clinical documents.
Optimize document processing using language models and cloud services for classification, entity and relationship extraction, summarization, metadata generation, quality validation and traceability.
Implement and tune retrieval strategies using embeddings, vector databases, keyword search, metadata filtering, hybrid search and reranking to improve relevance, grounding and response quality.
Evaluate and support the migration and optimization of enterprise search indexes and vector data stores, including schema design, indexing strategies, performance testing, data refresh patterns and operational controls.
Build and expand LLM-based solutions on Amazon Web Services (AWS) Bedrock, including prompt and model integration patterns, guardrails, evaluation and production monitoring.
Develop and maintain RAG pipelines that connect governed enterprise content to conversational and agentic experiences.
Design graph data models and pipelines representing products, documents, requirements, concepts and relationships, and integrate graph retrieval into search and AI workflows.
Contribute to end-to-end chatbot delivery, including content ingestion, retrieval, service integration, conversation orchestration, evaluation, telemetry and production support.
Create secure and reliable APIs, services and integration patterns that expose derived data and AI capabilities to applications, agents and enterprise systems.
Implement automated testing, data quality controls and observability for pipelines and services, and troubleshoot complex production issues.
Improve solution performance, reliability, scalability and cost efficiency through measurement, experimentation, capacity planning and engineering automation.
Apply security-by-design, privacy-by-design and responsible AI practices, partnering with cybersecurity, legal, privacy, quality and platform teams to meet enterprise and regulated-environment requirements.
Participate in design and code reviews, define reusable engineering patterns and standards, document technical decisions and mentor junior engineers.
Collaborate with business and technical stakeholders to translate use-case needs into maintainable technical solutions and measurable outcomes.