Research Engineer/Scientist - Human Alignment, Consumer Devices
Develops RLHF and post-training methods for personalized, multimodal AI systems on consumer devices, focusing on reward modeling, preference learning, long-horizon evaluation, and alignment with user values. Requires strong ML research background in RLHF and related areas.
About the job
Responsibilities
- Develop RLHF and post-training methods for multimodal models.
- Build reward models and preference-learning pipelines for adaptive, personalized model behavior.
- Design datasets, rubrics, and evaluation frameworks that capture user preferences, contextual appropriateness, and long-term value in realistic tasks.
- Run experiments on policy improvement using explicit feedback, implicit signals, and model-based grading.
- Work on long-horizon evaluation problems, where model quality depends on behavior improving outcomes over time.
- Collaborate closely with safety researchers to ensure adaptation and personalization remain aligned, interpretable, and bounded by clear constraints.
- Prototype and iterate quickly on training recipes, reward formulations, data pipelines, and evaluation suites for product-relevant behaviors.
- Help define how success is measured for personalized AI systems including trust, appropriateness, and long-term user benefit.
Requirements
- Strong background in machine learning research, with experience in RLHF, reward modeling, preference optimization, or post-training for large models.
- Experience in one or more of: reinforcement learning, ranking, recommender systems, personalization, memory, or human-in-the-loop evaluation.
- Care about rigorous empirical work and know how to design clean experiments, reliable evals, and decision-useful metrics.
- Experience building datasets or eval pipelines grounded in human preferences, rubrics, or real-world product behavior.
- Comfortable working across the stack, from data generation and labeling strategy to training runs, reward functions, and analysis.
- Interest in multimodal AI and how models can learn from richer interaction signals over time.
Skills
RLHF, Reward Modeling, Preference Optimization, Reinforcement Learning, Multimodal Ai, Post-Training, Machine Learning, Evaluation Frameworks, Datasets, Policy Improvement
Similar jobs
AI Research jobs
OpenAI
San Francisco, CA
Researcher or engineer focused on designing, evaluating, and productionizing oversight systems and safety mitigations for autonomous AI agents. The role requires strong systems or security reasoning, threat-modeling ability, and experience building practical evaluations and controls.
OpenAI
San Francisco, CA
Researcher focused on training and evaluating frontier AI agents, mining incidents, and building scalable safety measurement systems. The role requires strong research or ML engineering execution, quantitative judgment, and the ability to own ambiguous projects end to end.
Anthropic
San Francisco, CA
Research Engineer building large-scale AI capability evaluations, telemetry, data pipelines, and analysis tools for Anthropic’s Takeoff Intel team. The role requires hands-on large language model experimentation, rapid prototyping, data expertise, and strong research collaboration.
Thinking Machines Lab
San Francisco, CA
Research role focused on improving agentic coding capabilities through reinforcement-learning training, synthetic data, coding environments, reward design, and evaluations. Requires strong Python engineering, scalable distributed-training experience, and a bachelor’s degree or equivalent; research experience and a PhD are preferred.
Thinking Machines Lab
San Francisco, CA
Conduct AI safety research across data curation, post-training, evaluations, synthetic data, and red-teaming to improve model reliability on harmful and dual-use requests. The role requires AI safety experience, Python, deep learning frameworks, and scalable technical research skills.