CareerPlanSign in

Research Scientist - Long-Horizon Multi-Agent Systems

San Francisco, CA💼 Full-time💰 $1–$1🗓 2026-03-12 → 2026-09-26

Core

Researching and building long-horizon multi-agent systems to outperform state-of-the-art in novel AI problems.

Role type

Research Scientist (Long-Horizon Multi-Agent Systems)

Builds

Novel AI systems for long-horizon reasoning, RL, and LLM post-training

Domain

Artificial Intelligence / Reinforcement Learning / Large Language Models

Deliverable

production ML models

Required skills

PhD in relevant field, publications at top conferences, long-horizon reasoning, Reinforcement Learning (RL), LLM post-training (RLHF, DPO, reward modelling), open-ended research

Preferred skills

None stated

Technologies

None stated

Responsibilities

Push novel ideas into working systems, execute knowledge across reasoning, RL, and memory, tackle problems without standardized solutions

Seniority

Early-career PhD to highly experienced

Sourced via techire · Listed on CareerPlan, which tracks 846,000+ jobs from 20+ sources.