companyReflection AI logo

Technical Staff Member - Post-Training

On-site Full-time

Clicking Apply Now takes you to AutoApply where you can tailor your resume and apply.


Unlock Your Potential

Generate Job-Optimized Resume

One Click And Our AI Optimizes Your Resume to Match The Job Description.

Is Your Resume Optimized For This Role?

Find Out If You're Highlighting The Right Skills And Fix What's Missing

Experience Level

Experience

Qualifications

To excel in this position, candidates should possess:A profound understanding of machine learning fundamentals combined with practical experience in training large-scale language models (LLMs). Strong engineering capabilities, with a comfort level in navigating complex machine learning codebases and distributed systems. Demonstrable experience in enhancing model behavior through data manipulation, reward modeling, or reinforcement learning methodologies. Evidence of managing ambitious research or engineering projects that resulted in significant model enhancements. A proactive attitude in a fast-paced startup environment, with a focus on effective execution. The ability to collaborate across varying teams and functions. Strong communication skills and a collaborative spirit. A passion for advancing the frontiers of intelligence.

About the job

Our Mission

At Reflection AI, our goal is to create open superintelligence and ensure its accessibility for everyone.

We are pioneering open weight models for various users, including individuals, enterprises, and even nation-states. Our talented team comprises AI researchers and industry veterans from leading organizations such as DeepMind, OpenAI, Google Brain, Meta, Character. AI, and Anthropic.

Role Overview

  • Develop systems that convert robust pre-trained models into aligned and versatile agents.

  • Lead research and engineering efforts to advance post-training practices, focusing on data curation and large-scale optimization.

  • Create data generation frameworks, reward models, reinforcement learning algorithms, and techniques for inference-time scaling.

  • Collaborate with both pre-training and post-training teams to achieve significant enhancements in model capabilities.

  • Help refine our understanding of how large models learn to reason, follow instructions, and evolve through reinforcement learning.

Your Profile

  • Solid grasp of machine learning principles with hands-on experience in large-scale LLM training.

  • Proficient engineering skills, with the ability to navigate intricate ML codebases and distributed systems.

  • Experience in enhancing model performance through data, reward modeling, or reinforcement learning techniques.

  • Track record of leading ambitious research or engineering projects resulting in measurable improvements.

  • Thrives in a dynamic, high-agency startup atmosphere; oriented towards action and clarity in execution.

  • Ability to work seamlessly across research and infrastructure boundaries.

  • Excellent communication skills and a collaborative mindset.

  • Driven by a passion for pushing the boundaries of intelligence.

What We Provide:

At Reflection AI, we believe that to truly build open superintelligence, it must be rooted in a strong foundation. By joining us, you will contribute to building from the ground up within a compact, highly skilled team. Together, we will shape the future of our company and the landscape of open foundational models.

We aim for you to accomplish the most impactful work of your career, with the assurance that you and your loved ones are well-supported.

About Reflection AI

Reflection AI is at the forefront of AI innovation, dedicated to developing open superintelligence accessible to everyone. Our team is composed of experts from leading companies in the AI sector, focused on creating transformative models for a diverse range of users.

Similar jobs

Tailoring 0 resumes

We'll move completed jobs to Ready to Apply automatically.