Agent Post-Training, Context Research

United States Digital Space LLC; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

United States Digital Space LLC is looking for a Context Researcher to scale compute on context in the Agent Post-Training team. This role involves collaborating with researchers and engineers on model training and improving product interfaces.

Your responsibilities will include designing experiments, owning improvements in the post-training stack, and partnering with product teams to enhance model behavior. The ideal candidate will have a strong background in machine learning and be comfortable tackling complex open-ended issues.

Qualifications

• Strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training.
• Ability to tackle open-ended problems requiring research and engineering execution.
• Comfortable working across research, product, and infrastructure boundaries.
• Desire to train and ship models that are useful for various users.

Responsibilities

• Design and run experiments to improve scaling of compute on context.
• Own improvements to the post-training stack including RL and data pipelines.
• Build environments that expose model failures for improvement.
• Partner with product teams to translate user needs into model enhancements.
• Debug failures in shipped models and formulate solutions.

Skills

Machine learning fundamentals

Software engineering

Systems and statistics

Experience with LLMs

Hands-on RL and evaluation

Job description

About the Team

The Agent Post-Training team creates the frontier agents the company ships to the world. We train models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve.

We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi‑agent coordination, long‑horizon execution, factuality, instruction following, calibrated reasoning, and taste.

Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what the company's next agents can do, then carry those capabilities through major training runs and into the products people use.

About the Role

We believe that the final enabler for AGI is spending compute on context. As a Context Researcher on Agent Post‑Training, you will scale compute spent on context. You will work in our frontier training stack on enabling the next paradigm of model training with a clear product interface for iterative deployment (Codex Chronicle). You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people. This is a high‑agency role for people who want their work to land directly in frontier models.

Responsibilities

• Design and run experiments that improve scaling of compute on context.
• Own end‑to‑end improvements to the post‑training stack, including RL, data pipelines, graders, reward signals, evals, diagnostics, and model‑behavior analysis.
• Build evals and environments that expose the next set of model failures, then turn those failures into training data, product fixes, or new research directions.
• Partner with Codex and ChatGPT product teams to understand what users need and translate product signal into model improvements.
• Work on early‑training and alignment interventions, including data mixtures, objectives, synthetic data, and eval loops that shape downstream agent behavior.
• Help decide which integrations, capabilities, and fixes are ready for inclusion in major model runs.
• Improve the machinery for large‑scale training and launch: experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness.
• Take on cross‑functional projects that touch model training, product infrastructure, and the production agent harness, such as multi‑agent systems or training directly against production‑like environments.
• Debug hard failures in shipped or near‑shipped models and turn messy qualitative behavior into concrete hypotheses, experiments, and fixes.

Qualifications

• Have strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field, and can learn quickly across the parts you have not worked in before.
• Have hands‑on experience with LLMs, RL, RLHF/RLAIF, post‑training, evals, graders, synthetic data, model training, coding agents, tool‑using agents, or production ML systems.
• Are excited by open‑ended problems where the path is unclear, the signal is noisy, and the right answer requires both research taste and engineering execution.
• Care about product impact and model behavior, not just benchmark movement. You have opinions about what makes an agent useful, reliable, honest, tasteful, and easy to work with.
• Can move from a vague behavioral problem to a concrete experiment: define the hypothesis, build the pipeline, run the model, analyze the result, and decide what to do next.
• Are comfortable working across research, product, infrastructure, data, evals, and safety boundaries, and can communicate clearly with each group.
• Like building load‑bearing systems and processes when that is what the team needs, even if the work is not glamorous.
• Want to train and ship the models that make agents genuinely useful for developers, enterprises, researchers, and everyday users.

Equal Opportunity Employer

We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. For additional information, please see the company’s affirmative action and equal employment opportunity policy statement.