Machine Learning Engineer: LLM Interpretability & Systems
$175k - $250k • Remote • San Francisco • FullTime
Posted 6mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
Machine Learning Engineer
About the job
CTGT provides a deterministic governance layer for AI workflows, enabling organizations to deploy generative models with confidence. Born out of Stanford University research, our lightweight, model-agnostic system enforces policy, prevents drift, and produces auditable decisions in real time. We bridge the gap between LLM capabilities and domain-specific requirements, bringing frontier intelligence into real-world environments to make large language models more reliable, controllable, and performant for Fortune 500 companies.
Responsibilities
- Translate mechanistic interpretability research into production-ready code.
- Work directly with model internals to enhance behavior and performance.
- Utilize techniques like activation patching and control vectors for targeted improvements.
- Develop evaluation and deployment pipelines for enterprise environments.
- Design and optimize feature-level intervention systems for deterministic policy enforcement.
Requirements
- Strong understanding of Transformer architectures and PyTorch internals.
- Proficiency in the mathematical foundations of deep learning.
- Experience training, fine-tuning, or optimizing models.
- Ability to read research papers, identify key aspects, and implement them.
- Proactive in identifying and resolving issues.
- Motivated by improving LLM reliability and controllability for enterprise applications.
Benefits
- Competitive base compensation
- Significant equity in a venture-backed company
- Real impact working on core AI governance systems
- Autonomy and trust to form and execute technical opinions