AI & Data Engineering Intern

Job Description

AI & Data Engineering Intern | BeOne

The Tone:
This is a internship at BeOne, located in San Carlos, CA. BeOne is a rapidly growing company with a dedicated mission to fight cancer, offering challenging opportunities for scientific and business professionals. This role provides hands-on experience crucial for enhancing enterprise data interaction by designing and building an AI-powered bot. The intern will blend data engineering, AI/ML integration, and backend development to enable intelligent querying and automated analytics.

The TL;DR
• Role: Internship
• Type: Temporary, Part-time
• Location: Hybrid, San Carlos, CA
• Pay: $30–$35 hourly
• Mission: Help design and build an AI-powered bot that interfaces with our enterprise data warehouse hosted on Amazon Redshift, enabling intelligent querying and conversational data access.
• Tech Stack: SQL, AWS, Amazon Redshift, Python, FastAPI, Flask, AWS Lambda, Amazon Bedrock, SageMaker, AWS Secrets Manager, Microsoft Outlook Integration, LLMs, OpenAI APIs, Databricks, REST APIs, star schema, fact/dimension tables

What You’ll Actually Do
• AI Bot Development: Design and build an AI-powered chatbot interface for querying Redshift data.
• NL2SQL Implementation: Implement Natural Language to SQL (NL2SQL) pipelines to translate user prompts into executable code.
• Data Engineering: Understand Redshift data models, create metadata, and optimize SQL queries while implementing guardrails.
• Backend Services: Develop Python-based backend services (FastAPI/Flask) to manage data flow between the UI, LLM, and Redshift.
• Cloud Integration: Work with AWS services like Lambda, Bedrock/SageMaker, and Secrets Manager for secure, serverless operations.

The Must-Haves
• Background: Actively enrolled in a university undergrad degree program (entering junior year or above with a 3.0 GPA) OR enrolled in a master’s or PhD Program. Currently pursuing a degree in Computer Science, Data Science, AI, or a related field. Understanding of relational databases, data warehousing, machine learning, and data modeling concepts.
• Experience: Hands-on experience with Databricks. Strong knowledge in AWS, Redshift, and SQL (query optimization, joins, aggregations, CTEs). Basic experience with Python. Familiarity with REST APIs, AI/LLMs, and prompt engineering, including LLM APIs (e.g., OpenAI).
• Skills: SQL, Python, AWS, Data Modeling, Prompt Engineering
• Bonus: Interest in AI/LLMs and prompt engineering.