About The Position

BeOne continues to grow at a rapid pace with challenging and exciting opportunities for experienced professionals. When considering candidates, we look for scientific and business professionals who are highly motivated, collaborative, and most importantly, share our passionate interest in fighting cancer. Internship program dates: June 8 - August 21, 2026 This is an in person role - our ideal candidate will come to San Carlos office every week Tuesday & Wednesdays or other days as needed. We are unable to offer relocation assistance. Education Required: Interns must be actively enrolled in a university undergrad degree program (entering junior year or above preferred; with a 3.0 GPA) or enrolled in master’s or PhD Program. Currently pursuing a degree in Computer Science, Data Science, AI, or related field. General Description/Scope of Responsibilities (Internship): Data and Analytics Internship offers hands-on experience in data modeling, ETL, visualization, data quality checks, and reporting using SQL, AWS. We are seeking a motivated AI & Data Engineering Intern to help design and build an AI-powered bot that interfaces with our enterprise data warehouse hosted on Amazon Redshift. This role blends data engineering, AI/ML integration, and backend development to enable intelligent querying, analytics automation, and conversational data access.

Requirements

  • Understanding of relational data bases, data warehousing, machine learning, Data modeling concepts (star schema, fact/dimension tables)
  • Hands-on experience on Databricks
  • Strong knowledge in AWS, Redshift, SQL (query optimization, joins, aggregations, CTEs)
  • Basic experience with Python.
  • Familiarity with REST APIs, AI/LLMs and prompt engineering
  • Interest in AI/LLMs and prompt engineering.

Nice To Haves

  • Familiarity with LLM APIs (e.g., OpenAI).

Responsibilities

  • AI Bot Development Assist in designing and building an AI-powered chatbot interface for querying Redshift data.
  • Implement NL2SQL pipelines (Natural Language to SQL) to translate user prompts into executable code.
  • Metadata Management: Create and maintain table/column descriptions within Redshift to provide the LLM with necessary context.
  • Prompt Engineering: Build and test evaluation pipelines to ensure generated SQL is accurate and functional.
  • Data Engineering & Redshift Optimization Schema Interpretation: Understand Redshift data models and create comprehensive metadata/documentation to feed into the AI context.
  • Query Guardrails: Write and optimize SQL queries while implementing logic to prevent "expensive" or "destructive" queries.
  • Performance Tuning: Support data transformations and create views/materialized views to simplify the data structure for the AI Input
  • Backend & AWS Integration Service Development: Build Python-based backend services (FastAPI/Flask) to handle the flow between the UI, the LLM, and Redshift.
  • Secure Execution: Handle authentication and secure query execution.
  • Cloud Infrastructure: Work with AWS services including: AWS Lambda for serverless execution. Amazon Bedrock (or SageMaker) for accessing LLMs. AWS Secrets Manager for secure Redshift credential handling.
  • Microsoft Outlook Integration with AWS

Benefits

  • All Company employees have the opportunity to own shares of BeOne Medicines Ltd. stock because all employees are eligible for discretionary equity awards and to voluntarily participate in the Employee Stock Purchase Plan.
  • The Company has a comprehensive benefits package that includes Medical, Dental, Vision, 401(k), FSA/HSA, Life Insurance, Paid Time Off, and Wellness.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service