What are the responsibilities and job description for the Technical Staff, Data - SF position at ReflectionAI?
About Reflection AI
At Reflection AI, we are building state-of-the-art intelligent agents, scalable training systems, and research-first principles.
Our team includes researchers and engineers who have been at the frontier of model development—spanning reinforcement learning, sequence modeling, and large-scale distributed training. We work on foundational challenges in autonomy, planning, and generalization.
This is a rare opportunity to shape next-generation systems through rigorous research, thoughtful engineering, and deep collaboration.
As a member of the Data Team at Reflection, you will play a pivotal role in our data strategy for training and evaluations. This is an interdisciplinary role that primarily requires engineering, research, and communication skills, along with a sharp attention to detail and willingness to “roll up your sleeves” and look at the data.
What you will do
At Reflection AI, we are building state-of-the-art intelligent agents, scalable training systems, and research-first principles.
Our team includes researchers and engineers who have been at the frontier of model development—spanning reinforcement learning, sequence modeling, and large-scale distributed training. We work on foundational challenges in autonomy, planning, and generalization.
This is a rare opportunity to shape next-generation systems through rigorous research, thoughtful engineering, and deep collaboration.
As a member of the Data Team at Reflection, you will play a pivotal role in our data strategy for training and evaluations. This is an interdisciplinary role that primarily requires engineering, research, and communication skills, along with a sharp attention to detail and willingness to “roll up your sleeves” and look at the data.
What you will do
- Conduct cutting-edge research in:
- Reinforcement learning for reasoning and planning (long-horizon, hierarchical control)
- Agentic capabilities and generalization
- Lead Data and RL environment initiatives:
- Curate dataset mixtures and design learning curricula (exploration, rewards, scaling laws)
- Implement ML data pipelines for large-scale RL training
- Scrape, collect and curate training and evaluation data
- Build and maintain custom RL environments and evaluation benchmarks
- Collaborate with a world-class research team to publish and open-source impactful work
- Keep up with the latest advancements in agentic and LLM-based research, and bring relevant ideas into our systems
- Strong background in LLMs and/or reinforcement learning
- Demonstrated ability to carry out end-to-end ML research (problem formulation, experimentation, analysis)
- Experience training large-scale models or working with distributed training infrastructure
- A publication record in top ML conferences (NeurIPS, ICML, ICLR, etc.) is a strong plus
- Familiarity with RL environments is a plus
- The opportunity to work at the forefront of AI research and data collection for training cutting-edge models.
- Collaboration with a team of world-class researchers and engineers from top AI labs and companies.
- Competitive compensation and benefits, with opportunities for professional growth.
