Mid-level Business Intelligence Analyst

Boeing Boeing · Aerospace · Seattle, WA +3

This role focuses on integrating Generative AI (GenAI) and Large Language Models (LLMs) into Business Intelligence (BI) workflows. The analyst will prototype and evaluate GenAI use cases, apply prompt engineering best practices, integrate LLM capabilities with BI tools, and ensure responsible AI use. They will collaborate with data scientists and ML engineers, develop training materials, and work with cloud data platforms. The role requires experience in BI, SQL, cloud platforms, and Python/R, with a strong emphasis on applying GenAI to analytics and automating workflows.

What you'd actually do

  1. Prototype and evaluate GenAI/LLM use cases to augment BI workflows (e.g., natural-language querying, automated data summarization, intelligent insights generation, prompt templates for analysts)
  2. Apply prompt engineering best practices: design, test, and optimize prompts and chains for consistent, accurate outputs; document prompt libraries and guardrails
  3. Integrate LLM/GenAI capabilities with BI tools or data platforms where appropriate (e.g., Application Programming Interfaces (APIs), wrappers, microservices) in collaboration with engineers and data scientists
  4. Ensure responsible use of GenAI: implement data privacy, Personally Identifiable Information (PII) handling, output validation, and model risk mitigation practices
  5. Collaborate with data scientists, Machine Learning (ML) engineers, and platform teams on productionizing Artificial Intelligence (AI)-enabled features and understanding model performance and limitations

Skills

Required

  • SQL
  • relational databases (Oracle, Teradata, SQL Server)
  • cloud platforms (GCP and/or AWS)
  • core data services (storage, ETL/streaming, warehouses, serverless computing)
  • building data products on cloud platforms (ingestion, transformation, cataloging, serving)
  • BI/visualization tools such as Tableau and/or Power BI
  • design scalable dashboards and data models
  • Python and/or R for data preparation, analysis, and/or prototyping
  • data modeling
  • ETL patterns
  • data quality practices
  • common BI architecture
  • Agile
  • DevOps
  • release methodologies

Nice to have

  • GenAI/LLM tools and APIs (e.g., OpenAI, Anthropic, Azure OpenAI, or on-prem alternatives)
  • prompt engineering for analytics use cases
  • building and/or integrating LLM-powered features: natural-language-to-SQL, summary/explainability layers, intelligent alerting, and/or conversational analytics
  • model operationalization concepts (MLOps), versioning, monitoring, and latency/throughput tradeoffs
  • secure and compliant handling of data when using LLMs, including PII redaction techniques and enterprise governance practices
  • automation frameworks, orchestration (Airflow, Prefect), and/or microservice APIs for embedding GenAI into workflows
  • prototyping production-ready PoCs that demonstrate measurable business value from GenAI and/or ML enhancements
  • scripting and tooling for prompt testing, evaluation metrics, and prompt libraries
  • cloud-native managed services on GCP and AWS for data products (e.g., BigQuery, Dataflow, Dataproc, Cloud Composer, S3, Redshift, Glue, Lambda)

What the JD emphasized

  • practical familiarity with Generative Artificial Intelligence (GenAI) and prompt engineering techniques
  • Prototype and evaluate GenAI/LLM use cases
  • Apply prompt engineering best practices
  • Integrate LLM/GenAI capabilities
  • responsible use of GenAI
  • Collaborate with data scientists, Machine Learning (ML) engineers

Other signals

  • prototyping GenAI/LLM use cases
  • prompt engineering
  • integrating LLM/GenAI capabilities
  • responsible use of GenAI
  • collaborate with data scientists, ML engineers