San Francisco, United States
Machine Learning Engineer: LLM Interpretability & Systems
CTGT · San Francisco · United States
- Contract
- Full time
- Occupation
- Data Scientist
Posted: 3/27/2026 · Last checked: 11/17/2026
Job description
Quoted in full from CTGT's job posting. Gavroche does not edit it.
About CTGT & The Mission
Despite massive investment in commercial AI, organizations 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 the most important global institutions 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 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 domain-specific requirements, we unlock the true potential of generative AI to solve the most pressing problems in our world today.
The Role
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 don’t think, “What’s a better prompt?”, but “How do I improve its fundamentals?”
CTGT’s Senior Machine Learning Engineer will operate deep within the model stack, working directly with weights, activations, and architectures to build the systems that make AI governance deterministic. Your work powers the Policy Engine, the core technology that gives enterprises real-time, auditable control over model behavior in production. Your mandate is ostensibly simple but difficult in execution: determine how a model can be improved for a specific purpose and build the systems that operationalize that within our platform.
As opposed to simply using models, you will probe the mechanics of their cognition.
What You Will Do
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.
Who You Are
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.
Our Stack
Languages: Python, Rust, and Node/TypeScript, with React on the frontend
Data: Postgresql, vector, and graph databases
Infra: Docker, Kubernetes, Terraform, across several cloud providers and customer VPCs
ML: Self hosted models on multiple GPU providers and frontier APIs
What We Offer
Compensation & Equity: Competitive base compensation, plus significant equity in a venture-backed company with institutional investors including Google’s Gradient Ventures, General Catalyst, and Y Combinator. 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 ships into real, high-stakes environments where governance, auditability, and performance are non-negotiable.
Autonomy & Trust: We operate with a high degree of trust. You are expected to form strong technical opinions and execute on them.
From Gavroche data
Figures computed from live adverts on Gavroche; the job text above is the employer's.
Similar roles in San Francisco
- Staff Data Scientist - Product Marketing · Chime Financial, Inc, San Francisco
- Partner Applied AI Engineer - AWS · OpenAI, San Francisco
- Machine Learning Engineer · Watney, San Francisco
- Staff Machine Learning Engineer · Watney, San Francisco
- Member of Technical Staff - Applied AI Engineer - Core Capabilities · Valthos, San Francisco
- Machine Learning Engineer · Raydar, San Francisco
200 open roles like this one; at most three per employer shown.
What data scientist adverts in the United States state
Middle half: 176,500 – 248,050 USD a year; median 205,000 USD.
From 395 adverts by 155 employers that state a salary, annualised.
How data scientist roles in the United States are worked
3% fully remote · 1% hybrid · 96% do not say
Of 272 adverts. An advert that does not state a work mode is counted as not saying, not as on-site.
New openings in San Francisco, by week
- 8/24/2026 323
- 8/31/2026 415
- 9/7/2026 365
- 9/14/2026 446
- 9/21/2026 515
- 9/28/2026 623
- 10/5/2026 574
- 10/12/2026 683
- 10/19/2026 562
- 10/26/2026 562
- 11/2/2026 602
- 11/9/2026 554
- 11/16/2026 44
6,268 openings over 12 weeks, by the week they were published.
Other roles at CTGT
- Senior Software Engineer · San Francisco
- Software Engineering Intern - Summer 2027 · San Francisco
2 open.