Ancestry.com LLC logo

Data Science - AI Document Understanding, Co-op

Job Overview

Location

Remote

Job Type

Full-time

Category

Software Engineering

Date Posted

June 6, 2026

Full Job Description

đź“‹ Description

  • • Design and implement AI-native agentic systems to extract and organize text and image data from billions of historical and genealogical records, including newspapers, city directories, family history books, and vital records (birth, marriage, death).
  • • Apply state-of-the-art AI techniques for Document Understanding tasks such as OCR/HTR, transcription, Named Entity Recognition (NER), Relation Extraction (RE), Coreference Resolution, Summarization, and Knowledge Graph construction.
  • • Analyze and optimize multi-modal models in zero-shot and few-shot learning scenarios to enhance document comprehension across diverse historical datasets.
  • • Architect multi-agent workflows using frameworks like LangChain, LangGraph, CrewAI, or AutoGen to automate complex, multi-step reasoning tasks in historical record analysis.
  • • Develop and deploy LLM-as-a-Judge evaluation frameworks using tools such as Arize Phoenix, DeepEval, or RAGAS to detect hallucinations, drift, and bias in AI-generated outputs.
  • • Collaborate with ML Ops and Data Science Engineering teams to deploy datasets, models, and pipelines into cloud environments including GCP, AWS EC2, S3, SageMaker, Model Registry, and Bedrock.
  • • Optimize AI model inference using techniques such as vLLM, LoRA, QLoRA, and quantization to improve efficiency and scalability in production systems.
  • • Work with transformer models, embeddings, and vector databases to enhance retrieval and reasoning capabilities in genealogical data systems.
  • • Utilize Python and libraries including Hugging Face Transformers and agentic frameworks (LangChain, LangGraph, CrewAI, AgentCore) to build and test AI solutions.
  • • Communicate technical findings, model performance metrics, and proposed solutions clearly to both technical teams and non-technical stakeholders, including executives.
  • • Contribute to product development, customer success, and content creation initiatives by enabling automated understanding of historical documents that enrich family history discovery.
  • • Operate as a part-time, work-study co-op role while actively enrolled in a Master’s or PhD program in a quantitative field.

🎯 Requirements

  • • Currently pursuing a Master’s or PhD in Computer Science, Data Science, Statistics, Mathematics, Linguistics, Engineering, or a related quantitative field
  • • Specialization in AI and Large Language Models (LLMs) with familiarity with GPT, Gemini, Qwen, Llama, Claude, or similar foundational models
  • • Experience with inference optimization techniques such as vLLM, LoRA, QLoRA, and quantization
  • • Strong proficiency in Python and libraries including Hugging Face Transformers, LangChain, LangGraph, CrewAI, and AgentCore
  • • Familiarity with transformer models, embeddings, vector databases, and multi-modal AI systems
  • • Software development experience with cloud platforms (GCP, AWS EC2, S3, SageMaker, Model Registry, Bedrock) preferred

🏖️ Benefits

  • • Remote work flexibility with options to work from home or nearest office (subject to role eligibility)
  • • Opportunity to contribute to meaningful work that enriches people’s understanding of their family history
  • • Hands-on experience with cutting-edge AI technologies and large-scale historical datasets
  • • Collaboration with cross-functional engineering and data science teams in a human-centered, inclusive environment
  • • Work-study co-op structure designed to support ongoing academic progress
  • • Equal opportunity employer committed to diversity, inclusion, and reasonable accommodations

Skills & Technologies

Python
AWS
GCP
Remote
Degree Required

Ready to Apply?

You will be redirected to an external site to apply.

Ancestry.com LLC logo
Ancestry.com LLC
Visit Website

About Ancestry.com LLC

Ancestry.com LLC is a leading genealogy and family history company that provides consumers with access to historical records, DNA testing services, and family tree-building tools. The company operates a subscription-based platform that enables users to explore their ancestry through digitized archives, census data, vital records, and user-contributed family trees. Ancestry also offers AncestryDNA, a direct-to-consumer genetic testing service that helps individuals uncover ethnic origins and connect with genetic relatives. Headquartered in Lehi, Utah, Ancestry serves millions of customers worldwide and leverages data science and AI to enhance record matching, ethnicity estimates, and historical insights. The company combines technology, content, and community to help people discover, preserve, and share their family history.

Get more remote jobs like this

Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.

Newsletter

Weekly remote jobs and featured talent.

No spam. Only curated remote roles and product updates. You can unsubscribe anytime.

Similar Opportunities

Expired
Any Location / Remote
Full-time
Expired May 2, 2026
GitLab
Remote
Degree Required

3 months ago

Apply
Expires soon
Remote: ANZ
Full-time
Expires Jun 13, 2026 (Soon)
Python
JavaScript
GCP
+5 more

2 months ago

Apply
Expires soon
Sedgwick Claims Management Services, Inc. logo

Sedgwick Claims Management Services, Inc.

US Telecommuter
Full-time
Expires Jun 11, 2026 (Soon)
Remote
$18-32/hr
Degree Required

2 months ago

Apply
Expires soon
Remote
Full-time
Expires Jun 14, 2026 (Soon)
Remote

2 months ago

Apply