Junior AI Infra Engineer: Build Scalable Open-Source AI

Deep Infra Inc.; Palo Alto (CA); On-site; USD 140,000 - 150,000; Full time

Job summary

DeepInfra is building the infrastructure layer for the next generation of AI. We’re seeking early-career Software Engineers (0-2 years) to join our team in Palo Alto.

You will design, build, and scale production AI model serving, collaborating with experienced engineers and contributing to high-impact systems. Ideal candidates have completed or are in the final year of a CS/CE degree, strong fundamentals in algorithms, and hands-on experience with Python and ML libraries.

Qualifications

• Bachelor’s or Master’s degree in CS/CE or related field (completed or in final year).
• Strong fundamentals in data structures, algorithms, and software design.
• Proficiency in Python and AI/ML libraries (NumPy, pandas, SciPy, TensorFlow, PyTorch).
• Experience with AI/ML through coursework, research, projects, or internships.

Responsibilities

• Collaborate with engineers to design, develop, and test inference solutions for state-of-the-art AI models.
• Implement, optimize, and evaluate AI models using Python, C++, CUDA, and NCCL.
• Monitor and maintain production model-serving systems.
• Work on new features, fix bugs, and participate in code reviews.
• Participate in daily standups, design reviews, and team discussions.
• Explore new AI/ML techniques and tools, and experiment with improving model performance.

Skills

Data structures & algorithms

Problem-solving

Communication

Curiosity & learning

Education

Bachelor’s or Master’s degree in CS/CE or related field

Tools

Python

NumPy

pandas

SciPy

TensorFlow

PyTorch

Git

CUDA

NCCL

Job description

DeepInfra is building the infrastructure layer for the next generation of AI. We’re seeking early-career Software Engineers (0-2 years) to join our team in Palo Alto.

You will design, build, and scale production AI model serving, collaborating with experienced engineers and contributing to high-impact systems. Ideal candidates have completed or are in the final year of a CS/CE degree, strong fundamentals in algorithms, and hands-on experience with Python and ML libraries.