Research Engineer - Agency and Reasoning

Zyphra; San Francisco (CA); Sur place; USD 100 000 - 140 000; Plein temps

Avantages offerts par ce poste

Comprehensive medical, dental, vision, and FSA plans

Competitive compensation and 401(k) plan

Relocation and immigration support

In-office snacks and meals provided

Unlimited PTO and company holidays

Collaborative team environment

Résumé du poste

A cutting-edge AI company based in San Francisco is seeking a Research Engineer specializing in Agency and Reasoning. The role focuses on performing research in reinforcement learning and applying innovative ideas to the next generation of their language models. Candidates should have a postgraduate degree in a scientific field and be proficient in PyTorch and Python. The company values creativity and provides a dynamic work environment with excellent benefits, including comprehensive health plans and unlimited PTO.

Qualifications

• Experience with reinforcement learning in language model reasoning.
• Proficient with language-model-supervised fine-tuning and preference-learning methods.
• Intuitive ability to understand model behaviors.

Responsabilités

• Contribute to the Agency and Reasoning Team.
• Perform novel research in reinforcement learning.
• Apply ideas to next generation of language models.

Connaissances

Reinforcement learning

Prototyping

Python

PyTorch

Data engineering

Collaborative skills

Formation

Postgraduate degree in a scientific subject

Outils

PyTorch

Python

Description du poste

Zyphra is an artificial intelligence company based in San Francisco, California.

The Role:

As a Research Engineer - Agency and Reasoning, you will be a core contributor to Zyphra’s Agency and Reasoning Team. You will be involved with performing novel research in reinforcement learning, post-training, and human preference learning, and applying your ideas at scale to our next generation of language models.

What We’re Looking For / Requirements:

• Strong research taste and intuition

• The ability to work through a research project from conception to execution to write-up

• Strong implementation and prototyping skillset

• A researcher who can take an idea from conception to experimentation extremely quickly

• The ability to work well and cooperate with others in a high-paced research setting

• Curiosity, interest, and joy in understanding intelligence.

Qualifications / Additional Skills:

• Experience and aptitude with reinforcement learning, either in the context of language model reasoning or more classical RL tasks

• Experience with language-model-supervised fine-tuning and preference-learning methods, such as DPO and simPO.

• Experience with context-length extension methods

• A good intuitive ability to understand model behaviors and correct them through iterative fine-tuning

• Interest in grappling in detail with data and spending significant time involved in data engineering and synthetic data generation

• Postgraduate degree in a scientific subject (Computer Science, EE/EECS, Mathematics, Physics)

• Previously published machine learning research in well-respected venues

• Highly proficient with PyTorch and Python

• We are excited and able to rapidly learn new fields and implement new ideas

• Excellent communication and collaboration skills, and can work effectively on both research and engineering implementation at scale

Why Work at Zyphra:

• Our research methodology is to make grounded, methodical steps toward ambitious goals. Both deep research and engineering excellence are equally valued

• We strongly value new and crazy ideas and are very willing to bet big on new ideas

• We move as quickly as we can; we aim to minimize the bar to impact as low as possible

• We all enjoy what we do and love discussing AI

Benefits and Perks:

• Comprehensive medical, dental, vision, and FSA plans

• Competitive compensation and 401(k) plan

• Relocation and immigration support on a case-by-case basis

• In-office snacks and meals provided

• Unlimited PTO and company holidays

• In-person team in San Francisco with a collaborative, high-energy environment