Summer Research Intern

Abakaai

Mountain View, CA, United States
On-site
High-quality dataset construction
Benchmark development for ai models
Evaluation pipeline creation
The role involves designing and constructing high-quality datasets and benchmarks for areas such as LLM reasoning, vision-language modeling, and 3D perception

Job Summary

  • The role involves designing and constructing high-quality datasets and benchmarks for areas such as LLM reasoning, vision-language modeling, and 3D perception.
  • Interns will work closely with the internal research team and external collaborators from the 2077AI Foundation to contribute to research artifacts used by leading AI labs.
  • Responsibilities include developing evaluation pipelines, conducting error taxonomy analysis, and supporting research on long-context modeling and data efficiency.

Matching Summary

The role involves designing and constructing high-quality datasets and benchmarks for areas such as LLM reasoning, vision-language modeling, and 3D perception.

Skills & Requirements

Must-have

  • High-quality dataset construction
  • Benchmark development for AI models
  • Evaluation pipeline creation
  • Error taxonomy and failure analysis
  • Multimodal model evaluation

Nice-to-have

  • Passion for evaluation science
  • Experience with open-source projects
  • Interest in applied AI research at scale
  • Collaboration with external research teams

Key Requirements

  • Graduate or PhD-level difficulty understanding
  • Background in computer science or related field
  • Strong analytical skills for failure analysis

Work Rights

Not specified

Tailored Resume

Cover Letter