Manifold Research Group tackles ambitious, high-impact research problems that traditional institutions overlook—those too engineering-intensive for academia and too exploratory for industry. Inspired by coordinated research models like ARPAs and FROs, we assemble focused, cross-functional teams to systematically pursue and deliver paradigm-shifting science and technology.
Software Control Agents
The Software Control team is creating open source evaluation frameworks, training methodologies, and novel architectures for computer use agents that can understand GUIs, execute complex workflows via APIs, and adapt to diverse software interfaces. This research is foundational to realizing AI systems that can truly augment human productivity by operating any software tool, from IDEs to creative applications to enterprise systems, pushing us closer to genuinely useful AI assistants that work alongside humans in digital environments.
The Role
OS Team members form the core of Manifold Research Group. As an OS Research Fellow, you'll actively drive our ambitious projects—from initial roadmapping and technical implementation to writing impactful papers.
In this project, you'll be working on:
- Designing and implementing the next generation evaluation system for computer use agent models across diverse tasks and capabilities
- Curating, cleaning and generating diverse multimodal datasets to push the performance of state of the art software control models
- Researching and implementing post-training techniques including parameter-efficient fine-tuning methods such as LoRA/QLoRA and reinforcement learning methods such as RLVR.
- Training new kinds of software control models from scratch
- Building specialized simulations for software control models
- Contributing to research publications and open-source initiatives
Qualifications
Outstanding research emerges from driven, talented minds. For this project, we are looking for the following attributes:
- Demonstrated prior research experience, evidenced by published work in peer-reviewed conferences, journals, or recognized preprint platforms
- Strong skills in data collection, curation, and cleaning, particularly for multimodal datasets combining text, images, and action sequences
- Hands-on experience with profiling and running experiments with large language models (LLMs), including performance analysis, ablation studies, and systematic evaluation
- A foundation in probability theory, linear algebra, and optimization methods, with hands-on experience with prompt engineering, model fine-tuning and test-time scaling
- Interest and preliminary understanding of Computer Use Agent Models (CUAs) and their architectures, training procedures, and evaluation methodologies
- Proficiency with Python, JavaScript, and familiarity with Git, Linux (using the VMs on cloud) and web, OS architectures
- Proficiency with deep learning frameworks (PyTorch, JAX, or TensorFlow), with experience in distributed computing environments
Expectations
There are a few key expectations and clarifications we need to emphasize regarding the OS Research Team:
- Contribute approximately 10 hours per week to ensure meaningful progress and deep engagement with our projects. Flexibility around life commitments is understood; clear, proactive communication helps us support each other.
- Experience with being able to navigate the uncertainty of research w/ a high degree of autonomy.
- Our working language is English, and a strong proficiency is required to clearly communicate technical concepts without confusion or misunderstanding.
- This is a volunteer effort; none of us receive compensation of any kind—including monetary payment, academic credit, or other formal incentives. Our commitment is driven entirely by shared passion for impactful research.
- More information on OS Research Team expectations is available here.
We look forward to seeing your application!