"mechanistic interpretability" Jobs

9 open tech roles matching “mechanistic interpretability”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: Python, AI/ML, Interpretability. Every listing is re-checked daily and closed roles are removed.

Showing 9 of 9 results

Research Engineer, Interpretability Hybrid Visa

Anthropic San Francisco, CA $315k–$560k/yr Published 10 months ago

JAX CUDA Interpretability Java Go

Apply →

Research Scientist, Interpretability Hybrid Visa

Anthropic San Francisco, CA $350k–$850k/yr Published 10 months ago

LLMs Interpretability Mechanistic Interpretability Transformers Python

Apply →

[Expression of Interest] Research Manager, Interpretability Hybrid Visa

Anthropic San Francisco, CA $350k–$500k/yr Published 10 months ago

LLMs Machine Learning AI/ML Interpretability Transformers

Apply →

Forward Deployed Engineer

Join Goodfire as a Forward Deployed Engineer to integrate AI interpretability solutions with strategic partners.

Goodfire San Francisco, CA $200k–$325k/yr Published 5 months ago

JAX PyTorch Python

Flexible on stack 70% coding

Apply →

Chief of Staff Hybrid

Join Goodfire as Chief of Staff to enhance leadership effectiveness in a mission-driven AI research company.

Goodfire San Francisco, CA $300k–$500k/yr Published 1 year ago

AI/ML

AI-first team

Apply →

Senior Data Scientist, CompBio Hybrid

Join insitro as a Senior Data Scientist to leverage multimodal data for drug development in a vibrant biotech startup.

Insitro South San Francisco, CA $183k–$194k/yr Published 2 weeks ago

RNA-seq Machine Learning proteomics microscopy Bioengineering

Flexible on stack

Apply →

Senior Scientist, Biology Hybrid

Join Xaira Therapeutics as a Senior Scientist to drive preclinical programs in Inflammation and Immunology using AI tools.

Xaira Therapeutics South San Francisco, California, United States $140k–$170k/yr Published 2 weeks ago

RNAseq qPCR ELISA Luminex AI/ML

Apply →

Anthropic Fellows Program, AI Safety & Security Hybrid

Anthropic London, UK; Ontario, CAN; Remote-Friendly, United States; San Francisco, CA $17.6k–$17.6k/yr Published 5 months ago

Large Language Models Machine Learning Physics computer science Mathematics

Apply →

Principal Scientist, Biology

Join Xaira Therapeutics as a Principal Scientist to drive therapeutic program strategy in Inflammation and Immunology.

Xaira Therapeutics South San Francisco, California, United States $164k–$205k/yr Published 5 days ago

AI/ML immunology

70% coding

Apply →