Sciforium
Pre-training Research Engineer
- Location
- San Francisco, CA, US
- Arrangement
- On-site
- Employment type
- Full-time
- Posted
- 31 August 2026 (about a month ago)
Checked about a month agoApplications go to the employer, never to RoleSprint
About this role
Sciforium is an AI infrastructure company developing next-generation multimodal AI models and a proprietary, high-efficiency serving platform. Backed by multi-million-dollar funding and direct sponsorship from AMD with hands-on support from AMD engineers the team is scaling rapidly to build the full stack powering frontier AI models and real-time applications.
ABOUT THE ROLE
As a Pre-training Research Engineer, you’ll focus on model implementation, pertaining and scaling, and improving the quality of our byte-native and multimodal foundation models. You’ll build and iterate quickly on research ideas, contribute production-grade training code and infrastructure, and help deliver high-quality base models that can serve real-world use cases at scale.
KEY RESPONSIBILITIES
PRE-TRAINING & SCALING
- Train large byte-native and multimodal foundation models across massive, heterogeneous corpora.
- Implement and evaluate new model architectures, training objectives, and optimization methods.
- Develop stable pre-training recipes and run scaling experiments for novel architectures.
- Conduct ablations and analyze training dynamics, model behavior, and base-model quality.
- Work with data and distributed training engineers to improve training efficiency, reliability, and scalability.
MUST-HAVES
- 5+ years of experience in machine learning research or engineering, with a proven track record of developing and pre-training large language or multimodal foundation models.
- Software Engineering: Strong general software engineering skills, with the ability to write robust and performant training code.
- ML Foundations: Solid understanding of deep learning fundamentals and modern pre-training methods and literature.
- Research and Experimentation: Ability to quickly implement research ideas and evaluate them using clear baselines, ablations, metrics, and analysis.
- GPU and Distributed Training: Hands-on experience running training workloads in GPU-based environments, with familiarity with distributed training.
- Education: MS in Computer Science, Machine Learning, Artificial Intelligence, Mathematics, or a related field.
NICE-TO-HAVES
- PhD in Computer Science, Machine Learning, Artificial Intelligence, Mathematics, or a related field.
- JAX Ecosystem: Extensive experience with the JAX, Flax, and XLA stack.
- Large-Scale Distributed Training: Experience with multi-node pre-training using systems such as FSDP, ZeRO, or Megatron.
- Training Recipes and Scaling: Experience developing training recipes, ablations, or scaling experiments.
- Monitoring and Reproducibility: Experience owning end-to-end training and evaluation pipelines with monitoring and reproducibility.
EDUCATION
- MS or PhD in Computer Science, Machine Learning, Artificial Intelligence, Mathematics, or a related field.
BENEFITS INCLUDE
- Medical, dental, and vision insurance
- 401k plan
- Daily lunch, snacks, and beverages
- Flexible time off
- Competitive salary and equity
EQUAL OPPORTUNITY
Sciforium is an equal opportunity employer. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.
Work location
- San Francisco, CA, US
Related jobs
Ready to make a decision?
This role is either worth your time or it isn’t.
Analyze the posting against your experience, see the gaps clearly, and build the right materials only if the opportunity makes sense.
Nothing is submitted automatically. You choose what happens next.
About this listing
Published on Ashby under the board identifier Sciforium, which is the name the employer’s own job board carries. RoleSprint has not verified the company’s registered or trading name, so it is shown exactly as published rather than tidied up.
RoleSprint is not the employer and not a recruiter. Applications are made on the employer’s own site and never reach us; what RoleSprint does is help you decide whether a role is worth your time and prepare for it if it is.
Published 31 August 2026, last checked about a month ago. A posting stops being advertised here 90 days after the employer published it, and one the employer takes down is marked closed rather than quietly removed.