# Researcher, Alignment Science

**Company:** [OpenAI](https://hotfix.jobs/companies/openai)
**Location:** San Francisco, CA
**Role:** AI Research
**Salary:** $250k – $445k/yr
**Skills:** PyTorch, Python, Reinforcement Learning, LLMs, Model Evaluation, Preference Optimization, Scalable Oversight, Post-Training, Empirical Ml, Research Infrastructure
**Posted:** 2026-04-28

> Designs and runs experiments to improve AI model intent alignment, honesty, calibration, and robustness using RL and empirical ML methods. Trains/evaluates large models like LLMs and integrates techniques into production workflows.

## Job Description

## Responsibilities
- Design and implement alignment experiments focused on intent following, honesty, calibration, and robustness.
- Train and evaluate models using reinforcement learning, and other empirical ML methods.
- Develop evaluations for failure modes such as hallucination, instruction-following failures, reward hacking, covert actions, and scheming.
- Study methods that encourage models to verify their behavior and report shortcomings honestly, including confession-style training objectives.
- Build monitoring and inference-time interventions that ensure compliant behavior or surface model issues to users or downstream systems.
- Investigate how alignment methods scale with model capability, compute, data, context length, action length, and adversarial pressure.
- Integrate successful techniques into model training and deployment workflows.
- Produce externally publishable research when results advance the broader science of alignment.
- Collaborate with researchers and engineers across post-training, RL, evaluations, safety, and product-facing teams.

## Requirements
- Strong hands-on experience training, evaluating, or debugging large ML models, especially LLMs.
- Excellent engineering skills in **Python** and modern ML frameworks such as **PyTorch**.
- Mathematical rigor, quantitative taste, and comfort turning ambiguous research questions into measurable experiments.
- Experience with **reinforcement learning**, post-training, preference optimization, scalable oversight, model evaluation, or adjacent empirical ML research.
- Ability to operate with high independence.
- Enjoy fast-paced, collaborative research environments.
- Strong record in technical problem solving (e.g., competitive programming, math contests, systems work).
- Motivation to build trustworthy, honest, and reliable AI systems.

## Similar roles

- [Researcher, Alignment CoT Monitorability](https://hotfix.jobs/jobs/f7a16777-d1f6-4f3c-93c2-d554fa92d87a) - OpenAI - San Francisco, CA - $250k – $445k/yr
- [Simulation Researcher/Engineer](https://hotfix.jobs/jobs/0783f6ce-3002-437d-9cf5-ed0e195e9182) - Luma AI - Los Angeles, CA - $250k – $450k/yr
- [Research Scientist - World Model](https://hotfix.jobs/jobs/5faee58d-db07-4225-972f-d41693ba6fbe) - Luma AI - Los Angeles, CA - $250k – $450k/yr
- [Researcher, Alignment Training](https://hotfix.jobs/jobs/5d1388b9-49bc-4659-93e6-165aa8045734) - OpenAI - San Francisco, CA - $250k – $445k/yr
- [Research Scientist / Engineer – Foundation Model: Core Research](https://hotfix.jobs/jobs/23a08bb6-8ade-4b8b-8314-e007c0e95b88) - Luma AI - Palo Alto, CA - $250k – $450k/yr

**Apply:** https://hotfix.jobs/jobs/bff54247-c297-4539-aea0-bd99d7ea00b9
**Canonical:** https://hotfix.jobs/jobs/bff54247-c297-4539-aea0-bd99d7ea00b9