Applied Scientist, Agi , Agi Information

Amazon Amazon · Big Tech · Sunnyvale, CA · Applied Science

This role focuses on advancing knowledge graphs for the LLM era, specifically for LLM grounding and construction pipelines. It involves web-scale knowledge mining, fact verification, multilingual information retrieval, and agent memory over graphs. The primary responsibility is entity resolution for conflating facts from multiple sources into a single graph entity, requiring scalable, generic, and streaming data solutions. The role also touches upon agent memory, suggesting a secondary stage involvement.

What you'd actually do

  1. solve entity resolution to enable conflating facts from multiple sources into a single graph entity for each real world entity
  2. develop generic solutions that work fo all classes of data in AKG (e.g., people, places, movies, etc.), that cope with sparse, noisy data, that scale to hundreds of millions of entities, and that can handle streaming data
  3. define a roadmap to make progress incrementally
  4. insist on scientific rigor, leading by example

Skills

Required

  • machine learning
  • agent background
  • state-of-the-art techniques
  • building models for business application
  • PhD or Master's degree and 4+ years of CS, CE, ML or related field experience
  • Java
  • C++
  • Python
  • algorithms and data structures
  • parsing
  • numerical optimization
  • data mining
  • parallel and distributed computing
  • high-performance computing

Nice to have

  • Master's degree or above in computer science, electrical engineering, or related field

What the JD emphasized

  • strong publication record
  • track record of delivering to customers
  • rapid experimentation

Other signals

  • knowledge graph construction pipelines
  • LLM grounding
  • entity resolution
  • streaming data