Machine Learning Engineer: LLM Interpretability & Systems
Develops systems for LLM interpretability and deterministic governance by working directly with model weights, activations, and architectures. Implements mechanistic interpretability techniques like activation patching and control vectors for enterprise policy enforcement in production.
About the job
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.
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.
Skills
PyTorch, Transformers, Mechanistic Interpretability, Activation Patching, Control Vectors, Feature Extraction, LLMs, Deep Learning, Fine-Tuning, Model Optimization
Similar jobs
ML Engineering jobs
Mirage
New York, NY
Build and deploy agentic systems that power AI-driven creative video workflows. The role requires 5+ years of experience, production ML or agentic pipeline development, context engineering, and expertise in evaluation and agent infrastructure.
Mirage
New York, NY
Build and advance agentic machine-learning systems for multimodal creative tasks, with a focus on video understanding, reasoning, control, and tool use. The role requires strong production ML or agent-pipeline experience and deep knowledge of modern LLM techniques.
Taste Labs
San Francisco, CA
Build evaluation methods, RL environments, agent tooling, and scalable infrastructure that make subjective qualities such as design and taste measurable for frontier AI models. The role requires experience with evaluations, RL environments, ML or post-training, plus strong backend engineering skills.
Mirage
New York, NY
Build and scale generative video and multimodal models, optimizing training and inference for efficiency, throughput, and ultra-low latency. The role requires deep learning systems expertise, strong PyTorch/CUDA experience, and the ability to move research models into production.
Clay
New York, NY
Build and ship production AI agents and the platform infrastructure that makes them reliable, steerable, and measurable. The role requires strong backend fundamentals, production LLM or agent experience, and expertise in evaluations, retrieval, orchestration, or tool-use design.