AI Data Platform Engineer

If you are unable to complete this application due to a disability, contact this employer to ask for an accommodation or an alternative application process.

Full Time NASA Safety Center, Cleveland, OH, US

4 days ago Requisition

BQMI has a rewarding position as an AI Data Platform Engineer. This is a new position and new capabilities within an established development team. The Customer is seeking an experienced team member who will design, build, deploy, and operationalize GenAI and data platform capabilities that implement and improve Customer Safety & Mission Assurance (SMA) use cases for the Organizational Safety & Mission Assurance Division.

The Customer's primary infrastructure is AWS. The team member will architect and grow a data lake that unifies structured, semi-structured, and unstructured sources (relational databases, documents, meeting transcripts, news/RSS feeds, M365/SharePoint content), expose those sources to AI workflows through secure APIs and Model Context Protocol (MCP) servers, and integrate with existing applications and enterprise identity, while meeting Customer policy, security, accessibility, and governance requirements.

• Architect, build, and operate a cloud data lake on AWS that ingests and organizes structured, semi-structured, and unstructured data from relational databases (e.g., SQL Server, managed RDS), object storage, documents, transcripts, RSS/news feeds, and M365/SharePoint sources, and makes that data AI-ready.
• Design and build end-to-end data pipelines: ingestion, transformation, document parsing and chunking, metadata enrichment, embedding generation, and loading into vector/semantic and structured stores, with orchestration, scheduling, data quality checks, and monitoring.
• Develop and operationalize retrieval-augmented generation (RAG) and agentic GenAI capabilities using AWS-native foundation model services and open frameworks, including knowledge bases, embeddings, vector search, natural-language-to-SQL, and tool use over the various datasets.
• Design, develop, secure, and document APIs and MCP servers that expose lake datasets and enterprise systems to LLM orchestrators, chat interfaces, and web applications as governed, discoverable tools.
• Implement authentication and authorization for AI services, APIs, and data access using OIDC/OAuth 2.0 and Microsoft Entra ; configure and administer identity providers (including Keycloak) for scopes, roles, service-to-service authentication, and federation.
• Build evaluation and observability for GenAI systems: retrieval quality, answer groundedness, hallucination detection, validation of NL-to-SQL outputs against source data, tracing, and cost/latency monitoring.
• Embed data governance into pipelines and retrieval: data classification and marking, document-level and row/column-level access controls, PII handling, lineage, and audit logging.
• Design and optimize prompts and agent workflows for large language models (LLMs) to ensure accurate, grounded, context-aware outputs with source citations.
• Evaluate and recommend tools: help the team select the right AWS services, open-source, and third-party components for each job based on capability, cost, security accreditation, and maintainability, avoiding over-engineering.
• Integrate AI capabilities into existing web applications, tools, training platforms, and M365/SharePoint solutions.
• Collaborate with subject-matter experts, engineers, data stewards, and mission programs to define use cases, gather requirements, and measure impact (e.g., reduced analysis time, improved risk foresight, higher detection accuracy).
• Ensure AI systems follow the Customer's "AI advises, humans decide" posture and responsible AI principles: human-in-the-loop review, source traceability, clear distinction between retrieved data and AI-generated content, explainability, robustness, safety, and compliance with federal guidelines (e.g., NIST AI Risk Management Framework, Customer AI governance).
• Stay current on frontier AI advances (e.g., agentic systems, the MCP ecosystem, trustworthy AI) and adapt them to constrained, high-assurance aerospace domains.
• Document architecture, pipelines, code, and processes to support reproducibility, audits, and knowledge transfer across the Customer organization.
• Must live within Greater Cleveland Area.
• No relocation funding available
• Bachelor's or Master's degree in Computer Science, Data Science, Artificial Intelligence, Engineering, or a related field (PhD preferred for…