Data Integration & AI Engineering Intern

About the Role

OPSiB is building a Retail Operations Intelligence platform. We are looking for an intern interested in data engineering, AI-assisted automation, and solving real-world technical problems.

What You'll Work On

• AI-assisted data mapping: Explore how AI/LLMs can identify relationships between source-system fields and OPSiB's standard data model.
• Data integration pipelines: Build workflows to ingest, transform, validate, and process data from APIs, CSV, Excel, and JSON sources.
• Schema matching: Help map different field names and data structures across POS, ERP, WMS, and other systems.
• Entity resolution: Develop approaches to identify when different product IDs, store IDs, or supplier IDs refer to the same real-world entity.
• Data quality and validation: Detect missing fields, inconsistent data types, duplicate records, invalid values, and conflicting identifiers.
• AI-powered automation: Experiment with LLMs and other techniques to suggest mappings, explain mismatches, and identify unresolved data problems.
• Configurable data models: Help design systems that can handle retailer-specific fields and mapping requirements.
• Testing and evaluation: Measure mapping accuracy, validate AI-generated suggestions, and ensure uncertain matches are routed for human review.

Requirements & Tech Stack

• Working knowledge of Python and data manipulation.
• Understanding of SQL, relational databases, tables, joins, and data types.
• Familiarity with structured data formats such as CSV, Excel, and JSON.
• Basic understanding of APIs and data retrieval from external systems.
• Understanding of data validation, schemas, field mapping, and transformation.
• Strong logical thinking, debugging skills, and willingness to investigate unfamiliar data.

Preferred

• Experience with Pandas and PostgreSQL.
• Familiarity with ETL/ELT pipelines and data modelling.
• Experience using LLM APIs such as OpenAI, Anthropic, or Gemini.
• Knowledge of structured LLM outputs, tool calling, embeddings, or AI-assisted automation.
• Experience with entity matching, schema matching, or data quality projects.
• Familiarity with FastAPI, Docker, or workflow orchestration.

Note: You don't need to know every technology listed. Strong fundamentals, practical problem-solving, and the ability to learn quickly are valued.

What We're Looking For in a Candidate

• Curiosity about how AI can solve actual engineering problems.
• Enjoyment of working with messy datasets, understanding inconsistencies, and designing reliable solutions.
• A candidate who has built a relevant data engineering or AI automation project will stand out.

What You'll Gain

• Hands-on experience building AI-assisted data integration workflows.
• Exposure to the challenges of connecting real-world enterprise data systems.
• Experience with data modelling, schema mapping, cross-system identifiers, and validation.
• The opportunity to contribute to an early-stage product's technical architecture.
• Practical experience evaluating when AI automation works and when deterministic logic or human approval is necessary.

How to Apply

Please share:

• Your resume or LinkedIn profile.
• Your GitHub profile or relevant project links, if available.
• A brief explanation of a data engineering, automation, or AI project you have worked on.

A project demonstrating Python, SQL, data mapping, API integration, or AI-assisted automation is particularly relevant.