Postdoctoral Fellow - Applied AI - Document Understanding

Ancestry

6d • Hybrid

About The Position

Ancestry is seeking an exceptional and highly motivated Postdoctoral Research Fellow to join our AI Applied Science Content team. This fellowship is designed for a researcher at the intersection of industry-scale data and academic rigor. In this role, you will lead research at the forefront of Document Understanding, designing and implementing AI-Native agentic systems to unlock insights from billions of historical and genealogical records. Your work will focus on advancing the state of the art in autonomous multi-agent workflows and on transforming unstructured historical records into structured, searchable knowledge that connects customers to their family history.

Requirements

• Ph.D. (or near completion) in Computer Science, Data Science, Statistics, Linguistics, Engineering, or a related quantitative field with a strong research focus.
• A strong record of academic publications in NLP, CV, or Agentic AI is preferred.
• Specialization in AI & LLMs, including familiarity with foundational models such as GPT, Gemini, Qwen, Llama, Claude, etc.
• Research in inference efficiency and optimization, potentially using vLLM, LoRA, QLoRA, and quantization approaches.
• Familiar with embeddings, vector databases, and transformer models, with software development experience.
• Strong proficiency in Python and relevant tools and libraries, including transformer models and multi-modal models.
• Ability to clearly present complex technical solutions to both technical and non-technical stakeholders

Nice To Haves

• Familiarity with cloud platforms and related AI/ML services such as Google Cloud Platform, GCP, Gemini API, Vertex AI, AWS EC2, S3, SageMaker, Model Registry, and Bedrock are a plus.
• NER, Relation Extraction, Coreference Resolution, Entity Resolution, Knowledge Graphs (Neo4j), spaCy, NLTK, BERT.
• Apply expertise using models like YOLO, Nougat, DONUT, OpenCV, etc. to perform layout analysis, identifying text blocks, headers, tables, and deeply nested lists.
• Establish ensemble models and "LLM-as-a-Judge" frameworks, and use tools like Arize Phoenix, DeepEval, or RAGAS to monitor or hallucination, drift, and bias.
• Familiarity with "AI coding" workflows and usage of AI coding assistants such as Amazon Q, Cursor, Claude Code, and Kiro to accelerate development cycles.

Responsibilities

• Implement cutting-edge AI solutions for key Document Understanding tasks such as OCR/HTR, transcription, Named Entity Recognition (NER), Relation Extraction (RE), Coreference Resolution, Summarization, and Knowledge Graphs working with diverse genealogical and historical collections spanning newspapers, city directories, family history books, and vital records (i.e., birth, marriage, & death records).
• Design and implement multi-agent workflows using frameworks like LangChain, LangGraph, CrewAI, AutoGen, AgentCore, Strands, Google ADK, A2A, etc. to automate complex multi-step reasoning tasks in historical document analysis and information extraction.
• Evaluate the performance of multi-modal AI & LLMs such as GPT, Gemini, Claude, Llama, and Qwen for zero-shot and few-shot scenarios in comprehensive document understanding.
• Apply expertise using models like YOLO, Nougat, DONUT, OpenCV, etc. to perform layout analysis, identifying text blocks, headers, tables, and deeply nested lists.
• Establish ensemble models and "LLM-as-a-Judge" frameworks, and use tools like Arize Phoenix, DeepEval, or RAGAS to monitor or hallucination, drift, and bias.
• Familiarity with "AI coding" workflows and usage of AI coding assistants such as Amazon Q, Cursor, Claude Code, and Kiro to accelerate development cycles.
• Partner with ML Ops to deploy datasets, models, and pipelines in cloud environments like AWS (S3, SageMaker, Bedrock, ECS, EKS) and GCP (Vertex AI, Gemini API).

Benefits

• Location flexible work approach, allowing you to choose to work in the nearest office, from your home, or a hybrid of both (subject to location restrictions and roles that are required to be in the office- see the full list of eligible US locations HERE).
• We will continue to hire and promote beyond the boundaries of our office locations, to enable broadened possibilities for employee diversity.
• We foster a work environment that's inclusive as well as diverse, and where our people can be themselves.
• Every idea and perspective is valued so that our products and services reflect the global and diverse clients we serve.
• Ancestry encourages applications from minorities, women, the disabled, protected veterans and all other qualified applicants.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Ph.D. or professional degree