[Remote] Research Engineer

Note: The job is a remote job and is open to candidates in USA. FAR.AI is a non-profit AI research institute dedicated to ensuring advanced AI is safe and beneficial for everyone. They are seeking Research Engineers to implement machine learning algorithms, run experiments, and analyze results as part of their AI safety research projects.

Responsibilities

• Implement machine learning algorithms, run experiments and analyze results
• Conducting pre- and post-release adversarial evaluations of frontier models; developing novel attacks to support this work; and exploring new threat models
• Maintaining GPU compute infrastructure to support experiments with open-weight models and developing new tooling to allow research teams to scale their fine-tuning and post-training workflows to frontier open-weight models
• Studying when lie detectors induce honesty or evasion, and developing for deception and sandbagging
• Working to rigorously solve security problems through building a science of security and robustness for AI, from demonstrating superhuman systems can be vulnerable, to scaling laws for robustness and jailbreaking constitutional classifiers
• Finding issues with Sparse Autoencoders, probing deception using AmongUs, understanding learned planning in SokoBan and interpretable data attribution
• Develop scalable implementations of machine learning algorithms and use them to run scientific experiments
• Contribute to open source codebases such as Pytorch, HuggingFace Transformers and Accelerate
• Involved in the write-up of results and credited as an author in papers
• Propose novel directions and join a research pod which suits interests

Skills

• Have significant software engineering experience or experience applying machine learning methods. Evidence of this may include prior work experience, open-source contributions, or academic publications
• Have experience with at least one object-oriented programming language (preferably Python)
• Are results-oriented and motivated by impactful research
• Common ML frameworks like PyTorch or TensorFlow
• Natural language processing or reinforcement learning
• Operating system internals and distributed systems
• Publications or open-source software contributions
• Basic linear algebra, calculus, probability, and statistics

Benefits

• We will also pay for work-related travel and equipment expenses.
• We offer catered lunch and dinner at our offices in Berkeley.

Company Overview

Company H1B Sponsorship