Machine Learning Engineer: LLM Interpretability & Systems

CTGT is a company focused on providing deterministic governance for AI workflows, ensuring enterprises can deploy AI with confidence. The Founding Senior Machine Learning Engineer will work on improving model performance and behavior, translating research into production code while directly interacting with model internals.

Responsibilities:

• Take ideas from mechanistic interpretability and related work, and turn them into code that runs in production, making research into reality
• Work directly with model internals to improve behavior and performance
• Leverage techniques like activation patching, control vectors, and feature extraction to push model performance
• Build the evaluation and deployment loops needed to ship changes reliably

Requirements:

• Strong understanding of Transformer architectures, PyTorch internals, and the mathematical foundations of deep learning
• Have trained, fine-tuned, or optimized models beyond superficial augmentation
• Can read a paper, decide what matters, and implement it
• Notice when something is not working and take ownership of fixing it
• Fundamentally aligned with CTGT's goal to democratize state-of-the-art AI capabilities through open-source optimization