Machine Learning Engineer: LLM Interpretability & Systems

CTGT • San Francisco, CA

6d

About The Position

CTGT is developing a deterministic governance layer for AI, enabling organizations to deploy generative models with confidence. Our 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 production environments to make AI more reliable, controllable, and performant. Our mission is to elevate models to the performance and accountability standards required by the Fortune 500.

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.
• Motivated by the challenge of making large language models reliable and controllable enough for the highest-stakes enterprise applications.

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 across commercial and open-source models.
• Leverage techniques like activation patching, control vectors, and feature extraction to achieve targeted, repeatable improvements in model output.
• Build the evaluation and deployment loops needed to ship changes reliably into enterprise environments.
• Design and optimize the feature-level intervention systems that enable deterministic policy enforcement at inference time.

Benefits

• Competitive base compensation
• Significant equity in a venture-backed company
• Institutional investors including Google’s Gradient Ventures, General Catalyst, and Y Combinator
• Work directly on the core systems that determine how models perform in the wild.
• Work ships into real, high-stakes environments where governance, auditability, and performance are non-negotiable.
• Operate with a high degree of trust.
• 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