Latest AI JobsBrowse Jobs
Thinking Machines logo

Research, Post-Training Evals

Thinking MachinesSan FranciscoResearch
Apply on company site
Salary
$350K - $475K USD
Job type
Full-time
Work mode
Remote
Posted
27 Aug 2026
Status
Open · checked 7d ago

About this role

Thinking Machines is hiring a full-time Research, Post-Training Evals professional to join the team in San Francisco with remote flexibility. This position suits individuals with a strong background in machine learning and evaluation methodologies who want to help build artificial intelligence that extends human will and judgment.

Role Overview

This position focuses on developing reliable model evaluations for research signals spanning creation, usability, auditing, and efficiency. The professional will collaborate closely with researchers and engineers across post-training and the wider research organization. Depending on individual background and interests, the researcher may concentrate on a single focus area or contribute across multiple evaluation challenges.

Key Responsibilities

Build internal evaluations and research signals for model capabilities and behaviors critical to research and post-training.
Design usability evaluations measuring real-world utility in research and product workflows while partnering with the data flywheel.
Enhance evaluation robustness by addressing grader reliability, ambiguous ground truth, evaluator disagreement, and behavioral gaps.
Establish benchmark auditing methodologies to ensure researchers can properly understand and trust evaluation signals.
Create specialized agentic evaluation environments, user simulators, and support harness development.
Assess personalized preferences, model biases, values, and nuanced behaviors alongside the post-training crafting team.

Requirements

Bachelor’s degree or equivalent practical experience in Computer Science, Machine Learning, Physics, Mathematics, or a related field.
Demonstrated background in designing, building, or analyzing evaluation systems, benchmarks, datasets, or graders.
Exceptional written and verbal communication abilities for cross-functional collaboration.

Nice to Have

Practical exposure to large language models, post-training, reinforcement learning, or agentic systems.
Experience working with evaluation auditing, human evaluations, LLM-judges, or open-ended task evaluation.
Familiarity with agentic harnesses, long-horizon tasks, or RL environments and preference evaluation.
A proven history of creating new evaluation methodologies that shaped model development.
Proficiency in Python alongside deep learning framework familiarity such as PyTorch, TensorFlow, or JAX.
Strong research judgment demonstrated through clean ablations, honest baselines, and technical writing.
A PhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline, or equivalent industry experience.

Skills and Tools

Python
PyTorch
TensorFlow
Large Language Models (LLMs)

Salary and Benefits

Annual base salary ranging from $350,000 to $475,000 USD, determined by background and experience.
Comprehensive health, dental, and vision benefits.
Unlimited paid time off (PTO).
Paid parental leave.
Relocation support and visa sponsorship availability.

About the Company

Thinking Machines aims to build artificial intelligence that expands human will and judgment. The organization trains frontier models using Inkling, creates Tinker to help individuals customize models, and designs interfaces that improve human-AI communication.

How to Apply

Interested candidates should visit the official Thinking Machines careers page to submit an application for this position.

Skills and tech stack

PythonPyTorchTensorFlowLLM

Questions candidates ask

What is the salary range for the Research, Post-Training Evals role?

The expected annual salary range is $350,000 to $475,000 USD, depending on background, skills, and experience.

Where is this job located?

This position is based in San Francisco, California, with remote flexibility.

Does Thinking Machines offer visa sponsorship?

Yes, Thinking Machines provides visa sponsorship and is committed to working through the process together for the right candidate.

What benefits are included with employment?

Benefits include generous health, dental, and vision coverage, unlimited paid time off, paid parental leave, and relocation support as needed.

What technical skills are required?

Candidates should be proficient in Python and familiar with deep learning frameworks such as PyTorch, TensorFlow, or JAX, alongside expertise in working with LLMs.

Ready to apply?

The application is on the official Thinking Machines careers page.

Apply on company site