Machine Learning Engineer: LLM Interpretability & Systems

CTGT • San Francisco, CA

30d

About The Position

Despite massive investment in commercial AI, enterprises often find that demonstrated value is elusive, primarily due to the non-deterministic risk inherent to generative models. CTGT is the deterministic governance layer that enables enterprises to deploy AI workflows with confidence.
Born out of Stanford University research, we provide the control plane that makes it possible. A lightweight, model-agnostic system that enforces policy, prevents drift, and produces auditable decisions in real time.
While we sit on the edge of AI research, CTGT brings frontier intelligence into real-world enterprise environments. We apply cutting-edge theory directly in production to make large language models more reliable, controllable, and performant in practice.
Our mission is to bring models to the level of performance and accountability required by the Fortune 500. By bridging the gap between LLM capabilities and enterprise requirements, we unlock the true potential of generative AI to solve the most pressing problems in our world today.
A new open-source model is released and you are compelled to reach inside and understand how it actually works. You instinctively try to push it beyond what most people say is already impressive. You observe model behavior and think, not how to prompt it better, but how to fundamentally improve it.
CTGT is on a mission to push the limits of what seems possible and our Founding Senior Machine Learning Engineer will operate deep within the model stack, working directly with weights, activations, and architectures to achieve just that. Your mandate is simple but exceptionally difficult: determine how a model can be improved for a specific purpose and build the systems that operationalize that within our platform.
This is not about using models. It’s about changing how they work.

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.

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.

Benefits

• Competitive Compensation & Meaningful Equity: Competitive salary and meaningful equity. We want people who think and act like owners.
• Real Impact: You will work directly on the core systems that determine how models perform in the wild. Your work will ship and be used in real enterprise environments.
• Autonomy & Trust: We operate with a high degree of trust. You are expected to form strong technical opinions and execute on them.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed