Jobs › Companies › Periodic Labs › Research Scientist, Scaling RL

Sobre este puesto de Research Scientist, Scaling RL en Periodic Labs

Periodic Labs · Presencial · Menlo Park, CA; Montreal, Canada

About Periodic Labs

We're an AI and physical sciences company building state-of-the-art models to accelerate breakthroughs across materials, energy, and beyond. Backed by world-class investors and growing rapidly, we operate at the pace the frontier requires. Our team brings deep expertise, genuine ownership, and a drive to push the boundaries of what's scientifically possible.

About the Role

We're training frontier models to develop deep scientific knowledge and reasoning for scientific tasks. You’ll study how RL scales with training compute, develop better algorithms, and take ideas from controlled experiments to our largest runs like Periodic Neon.

What You'll Do

  • Design experiments to understand how RL performance scales with compute, model size, data, and reward quality, building on work such as ScaleRL

  • Develop better RL algorithms, spanning policy optimization, advantage estimation, exploration, and credit assignment for long-horizon RL tasks

  • Build adaptive sampling and curriculum methods that adjust task difficulty, problem selection, and the number of rollouts as models improve

  • Study bias and stability during RL training, including importance-sampling corrections and methods to tackle policy staleness and training–inference mismatch, as discussed here.

  • Improve compute efficiency across training and inference through experiments with hyperparameters, such as length penalties, rollout counts, batch sizes, and update schedules.

You Will Thrive in This Role If You Have

  • Hands-on experience training LLMs with reinforcement learning

  • Strong attention to detail and rigorous approach to answer questions scientifically.

  • Coming up with small-scale RL setups that transfers to large-scale training runs.

  • Comfort working across a complex training stack to implement, debug, and test new research ideas.

  • We are open to offering a 1 year post-doc for this profile. Early career (final year PhD students) are encouraged to apply.

Mechanics
Minimum education: Bachelor’s degree or similar experience

Location: Menlo Park, CA or Montreal, Canada

Compensation: $225,000-$350,000 base + equity

Visa sponsorship: Yes, we sponsor visas and will do everything we can to assist in this process.

 
¿Listo para postularte en Periodic Labs?
Postúlate en Periodic Labs

Empleos similares

Periodic Labs
Research Scientist, Data
Periodic Labs
⚡ Postúlate pronto Menlo Park, CA Presencial 🛂 Patrocinio de visado
● Nuevo 👁 Visto ✓ Postulado hace 1 mes
Periodic Labs
Research Scientist, Condensed Matter Theory
Periodic Labs
⚡ Postúlate pronto Menlo Park, CA; Montreal, Cana... Presencial 🛂 Patrocinio de visado
● Nuevo 👁 Visto ✓ Postulado hace 1 mes
Nuro
Machine Learning Research Scientist, Prediction & Smart Agents
Nuro
⚡ Postúlate pronto Mountain View, California (HQ) Presencial $193,930–$291,150
● Nuevo 👁 Visto ✓ Postulado hace 9h
Nuro
Machine Learning Research Scientist, Active Learning
Nuro
⚡ Postúlate pronto Mountain View, California (HQ) Presencial $193,930–$291,150
● Nuevo 👁 Visto ✓ Postulado hace 9h
Tri
Research Scientist, Robot Learning - Continual Adaptation
Tri
⚡ Postúlate pronto Cambridge, MA Híbrido $158,400–$227,700
● Nuevo 👁 Visto ✓ Postulado hace 12h
Tri
Research Scientist, Robot Learning
Tri
⚡ Postúlate pronto Cambridge, MA Híbrido $158,400–$227,700
● Nuevo 👁 Visto ✓ Postulado hace 12h
HE
Senior Research Scientist, Multimodal Deep Learning and Risk Prediction
Heartflow
⚡ Postúlate pronto San Francisco, California Presencial $180,000–$240,000
● Nuevo 👁 Visto ✓ Postulado hace 13h
Baseten
Base Labs Research Scientist - RL Environments
Baseten
⚡ Postúlate pronto San Francisco Híbrido
● Nuevo 👁 Visto ✓ Postulado hace 15h
Biohub
AI Research Scientist Intern
Biohub
⚡ Postúlate pronto New York, NY (Hybrid); Redwood... Híbrido $133,994–$183,706
● Nuevo 👁 Visto ✓ Postulado hace 17h

Regístrate para recibir sugerencias adaptadas a los empleos que abres y las búsquedas que guardas.

Más empleos en Periodic Labs

Ver todos los empleos en Periodic Labs →

Postúlate ahora
🤖

Un momento — para

JobsRadar se creó para personas reales que están pasando un mal momento en su búsqueda de empleo — no para solicitudes automatizadas. Estás haciendo clic demasiado rápido y ahora estás bloqueado temporalmente.

Vuelve más tarde. Si de verdad estás buscando empleo, cuentas con nosotros — solo compórtate como una persona.

Catch your next role the second it’s posted.

Create a free account and we’ll watch the boards for you — the instant a job matches your search, it lands in your inbox or Telegram. No digging, no refreshing.

Create free account

Free forever · takes 30 seconds · already have one?

Toma ventaja en tu búsqueda de empleo.

Únete a nuestro canal de Telegram para lo que te ayuda a conseguir el puesto — referencias salariales, el pulso semanal del mercado y avisos de nuevas funciones. Sin spam, solo señal.

Únete al canal — es gratis