Member of Technical Staff - Post-Training
4 days ago
Highlight
OnsiteFull-timeEntry
Summary
Reflection AI is seeking a Member of Technical Staff - Post-Training to join their team in New York, NY. The role involves building systems that transform powerful pre-trained models into aligned and general agents.
About the Role
As a Member of Technical Staff - Post-Training, you will be responsible for driving research and engineering initiatives that push the frontier of post-training, developing data generation pipelines, reward models, reinforcement learning algorithms, and inference-time scaling techniques. You will collaborate across pre-training and post-training teams to deliver significant gains in model capability and contribute to understanding how large models learn to reason and improve through reinforcement learning.
About You
Required:
- Deep understanding of machine learning fundamentals and practical experience with large-scale LLM training.
- Strong engineering skills, comfortable diving into complex ML codebases and distributed systems.
- Experience improving model behavior through data, reward modeling, or RL techniques.
Preferred:
- Evidence of owning ambitious research or engineering agendas that led to measurable model improvements.
- Thrive in a fast-paced, high-agency startup environment; bias toward action and clarity of execution.
- Able to work fluidly across research and infra boundaries.
- Strong communication capabilities and comfort working collaboratively.
- Passionate about advancing the frontier of intelligence.
Benefits
- Top-tier compensation: Salary and equity structured to recognize and retain the best talent globally.
- Comprehensive medical, dental, vision, life, and disability insurance.
- Fully paid parental leave for all new parents, including adoptive and surrogate journeys.
- Financial support for family planning.
- Paid time off when you need it, relocation support, and more perks that optimize your time.
- Lunch and dinner provided daily, with regular off-sites and team celebrations.
ReflectionAI
Reflection was founded by former DeepMind and OpenAI researchers to build superintelligent coding agents. We previously built the most powerful LLM (ChatGPT, Gemini) and agent (AlphaGo, AlphaZero) systems in the world. At Reflection, we’re building autonomous AI systems that will soon help us accomplish virtually any cognitive task on a computer. We believe that coding is the root node problem that unlocks general computer use. In the near future large language models will interact with all software through code. https://tryasimov.reflection.ai/asimov-waitlist
New York, NY