About the role#
You will work directly with our engineering team to design, build, and deploy open-source AI models at scale. This role focuses on real engineering tasks rather than sandbox projects. You will contribute to systems that serve trillions of tokens, learning how to make software fast, efficient, and reliable.
What you'll do#
- Design, develop, and test inference solutions for top AI models.
- Implement and optimize models using Python, C++, CUDA, and NCCL.
- Monitor and maintain the live service.
- Handle feature development, bug fixing, and code reviews to ensure high-quality software delivery.
- Participate in daily stand-ups and design discussions.
- Stay current with industry trends in AI and machine learning.
- Try new things and ship code.
What you'll need#
- Current enrollment in a Bachelor's or Master's degree program in Computer Science, Computer Engineering, or a related field.
- Strong grasp of computer science fundamentals, including algorithms, data structures, and software design patterns.
- Proficiency in Python and experience with AI/ML frameworks like PyTorch, TensorFlow, NumPy, pandas, or SciPy.
- Familiarity with AI models, specifically Transformers and Diffusers.
- Experience with Git and agile development methodologies.
- Problem-solving skills with the ability to debug and optimize code.
- Strong communication skills to collaborate with cross-functional teams.
Location & details#
- Work modality: Remote.
- Employment type: Full-time internship.
- Compensation: Paid.
- Term: Rolling.
- Sponsorship: Not available.
About Deep Infra Inc.
Deep Infra Inc. operates in the technology and internet sector. Founded in 2022, the company is based in Palo Alto, California. It provides machine learning infrastructure and access to AI models via an API. The business also supports custom model deployment for its users. It currently maintains a staff of 2 to 10 employees.
How to get in at Deep Infra Inc.
Applying early to Deep Infra Inc. gives you a distinct advantage before the applicant pool grows. Intern Insider sends an instant alert the moment a role matching your target is published, helping you secure your spot among the first candidates. Getting your application in early ensures your profile is seen before the recruiter is overwhelmed by the pile. You can reach out to the recruiters behind these roles directly to ask about the position or a referral, which often improves your response rate. Intern Insider surfaces these specific contacts, allowing you to bypass the standard queue and connect with the team at Deep Infra Inc. on a professional level.
