INTERNSHIP - Data engineering & AI-ready software architecture
Core
Build a web interface and data pipeline to transform raw laboratory instrument output into clean, queryable results consumable by modern AI architectures (LLMs, RAG).
Role type
Data engineering & AI-ready software architecture intern
Builds
Standardized experimental data pipelines and LLM-queryable access layers for scientific teams
Domain
Bioinformatics / Laboratory data engineering
Deliverable
production ML models | product features
Required skills
Python, REST API design, Docker, Git, data indexing, LLM/agent integration patterns, JSON schemas
Preferred skills
Scientific/tabular data handling, bioinformatics exposure, microbiology context
Technologies
Streamlit, Python, Docker, Git, REST APIs
Responsibilities
Design automated extraction modules for heterogeneous instrument data; define unified data schemas; develop tools for AI agent querying; build internal visualization interfaces
Seniority
Intern
