Machine Learning Engineer: LLM Interpretability & Systems

CTGT
San Francisco
Workplace: OnsiteFull timeUSD 175,000 - 250,000 annuallyFunction: Data Science & Machine LearningSkills: ["Ownership","Communication","Problem-solving","Collaboration"]

Senior ML engineer with deep work on model internals, transformer architectures, and production-ready interpretability tooling to enable deterministic, auditable control of LLMs in enterprise environments. You will push research into production, improve model behavior across commercial/open-source models, and design intervention systems for policy enforcement at inference time.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
CTGT
CTGT
4 months ago

Machine Learning Engineer: LLM Interpretability & Systems

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 16 hours agoStatus: Live

Job Summary

Senior ML engineer with deep work on model internals, transformer architectures, and production-ready interpretability tooling to enable deterministic, auditable control of LLMs in enterprise environments. You will push research into production, improve model behavior across commercial/open-source models, and design intervention systems for policy enforcement at inference time.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Take ideas from mechanistic interpretability and related work and turn them into production-ready code.
  • •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.

Pay and Benefits

Salary: USD 175,000 - 250,000 annually

Key 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.
  • •Able to read a paper, decide what matters, and implement it.
  • •Take ownership of issues and fix them when something is not working.
  • •Motivated by making large language models reliable and controllable for high-stakes enterprise applications.
Experience:AIMLLLMEnterprise software
Skills:OwnershipCommunicationProblem-solvingCollaboration
Tech Stack:PyTorchTransformerDeep LearningProductionActivation patchingControl vectorsFeature extraction

Company Brief

CTGT
CTGT builds AI-driven software solutions that leverage machine learning to automate data analysis, generate insights, and streamline decision-making for enterprise clients across industries. Their platform focuses on scalable AI tooling, model deployment, and workflow integration to boost operational efficiency.
Industry: AI & Machine Learning
Website