Profile cover
A

AI Value Learning Preference Elicitation Engineer

Aria Watanabe

Full-time · Job · Los_Angeles

About the role

PyTorch, reinforcement learning, and large-scale preference datasets are the core of what we build at Velvix Labs. If human feedback is the raw material for alignment, this role is about getting that raw material right before any training happens. You'll design better methods for eliciting human preferences — moving past simple pairwise comparisons toward richer signals that capture why one response is preferred, not just which one. Then you'll turn that into training signal our reward models can actually use. We publish internally and encourage conference submissions, so this is interesting work: elicitation methodology is still an open research problem, and getting it wrong quietly degrades every downstream model we train.

Responsibilities

  • Design richer human preference elicitation methods beyond pairwise comparison
  • Build pipelines converting elicited preferences into reward model training signal
  • Run experiments comparing elicitation methods against downstream model quality
  • Collaborate with the reward modeling and RLHF research teams
  • Publish findings internally and support external conference submissions

Requirements

  • Strong PyTorch and reinforcement learning experience
  • Background in preference learning or RLHF research
  • Statistics experience for designing and analyzing elicitation experiments
  • Hugging Face experience for working with large model checkpoints
  • Comfort with open-ended, research-driven problems

Benefits

  • Fully remote
  • Significant equity package
  • Health, dental, and vision insurance
  • Conference and publication budget
  • Unlimited PTO

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

AI & Machine Learning Engineers

Skills

python pytorch statistics hugging face reinforcement learning

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior AI Researcher- Pre-training (f/m/d)

RemoteAI company

Full-time Senior

Senior AI R&D Engineer – Model Training (f/m/d)

RemoteAI company

Full-time Senior

AI Resident UK/EMEA

RemoteAI company

Full-time

Senior Machine Learning Engineer (Clinical Team)

RemoteAI company

Full-time Senior

Multimodal AI Model Optimization Research Engineer

RemoteAI company

Full-time

Conversational Modelling Research Engineer

RemoteAI company

Full-time

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$200k+ / year

AI Expertise

AI & Machine Learning Engineers

Skills

python pytorch statistics hugging face reinforcement learning

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in

Interested in this role? Create your free profile to apply.

Apply — create free profile