Applied AI Research Intern: Benchmark & Evaluation

Labelbox; San Francisco (CA); Hybrid; USD 35,000 - 45,000; Full time

Benefits offered by this job

Career advancement opportunities

Hybrid work model

Fast-paced environment

Job summary

A cutting-edge technology firm seeks an Applied Research intern to design and build evaluation systems for AI models. You'll create post-training datasets and prototype innovative training loops to improve real-world performance. Required qualifications include a strong background in AI, a relevant degree, and proficiency in Python and popular deep learning frameworks. Join a dynamic team focused on pushing the boundaries of AI and contributing to transformative technology in a hybrid work environment.

Qualifications

• Strong foundation in AI and machine learning.
• Deep understanding of multimodal models & data strategies.
• Passion for LLM evaluation and benchmarking.

Responsibilities

• Design and build evaluation and benchmark suites.
• Create post-training datasets at scale.
• Prototype RLHF-style training loops to improve performance.

Skills

Strong foundation in AI and machine learning

Proficiency in Python

Expertise in training data quality construction

Exceptional communication and collaboration skills

Education

Ph.D. or Master's degree in Computer Science, Machine Learning, AI

Tools

PyTorch

JAX

TensorFlow

Job description

A cutting-edge technology firm seeks an Applied Research intern to design and build evaluation systems for AI models. You'll create post-training datasets and prototype innovative training loops to improve real-world performance. Required qualifications include a strong background in AI, a relevant degree, and proficiency in Python and popular deep learning frameworks. Join a dynamic team focused on pushing the boundaries of AI and contributing to transformative technology in a hybrid work environment.