Graduate Research Co-op - AI & Representation Learning

Ancestry•Lehi, UT

1d•Hybrid

About The Position

Ancestry is a global leader in family history, connecting individuals with their past through an extensive collection of over 65 billion records, more than 3.5 million subscribers, and over 27 million people in its growing DNA network. The company is dedicated to a human-centered approach, valuing every person's story, and is committed to a location-flexible work approach, allowing employees to choose between working in an office, from home, or a hybrid model. Ancestry fosters an inclusive and diverse work environment, encouraging applications from minorities, women, the disabled, protected veterans, and all other qualified applicants. The DNA Science team is seeking a Graduate Research Co-op with strong experience in genomic data analysis and enthusiasm for human populations and/or family history. This part-time, work-study focused position, lasting 6 months, is designed for active master's and Ph.D. students. The role offers regular mentorship from scientists, providing valuable research experience and the opportunity to apply cutting-edge computational and statistical approaches to the world’s largest genomic and pedigree database to help people understand their ancestry, family, and themselves.

Requirements

Currently enrolled in a Graduate program (Ph.D. preferred, or MS) in Computer Science, Data Science, or a related quantitative field.
Solid understanding of Representation Learning, Embedding models, or Large-scale Data Modeling.
Proficient in Python and modern ML frameworks such as PyTorch or TensorFlow.
Strong analytical skills with the ability to extract meaningful insights from massive-scale, complex datasets.
A collaborative spirit and a desire to see research translated into real-world applications.

Nice To Haves

Familiarity with Vector Databases or Large Language Models (LLMs)

Responsibilities

Support the development of representation learning models to integrate massive-scale hierarchical data with diverse record sets.
Evaluate and benchmark diverse machine learning models to resolve data conflicts and improve the accuracy of relationship discovery at scale.
Assist in building scalable ML prototypes that analyze billions of data points to provide automated insights and personalization.
Develop efficient data pipelines to process and vectorize massive-scale datasets for downstream research and modeling tasks.
Collaborate closely with senior researchers to document findings and prepare technical reports on model performance and scalability.