ML Software Intern: Deploy & Optimize Models on CIM Chips

TetraMem - Accelerate The World; San Jose (CA); On-site; USD 48,000 - 62,000; Full time

Job summary

TetraMem invites a Software Intern to contribute to tools, frameworks, and applications enabling neural networks on our novel analog compute-in-memory chips. This internship sits at the intersection of software, hardware, and AI.

You will develop and optimize Python or C++ code for model compression, deployment, and runtime environments, and adapt ML models to improve efficiency on compute-in-memory hardware.

Qualifications

• Pursuing degree in CS, EE, or related field
• Strong programming experience in Python or C++
• Understanding of data structures, algorithms, and software architecture
• Familiarity with AI/ML frameworks (e.g., TensorFlow, PyTorch) is a plus
• Eagerness to learn and grow in a fast-paced environment

Responsibilities

• Develop and optimize Python or C++ code for neural network and model deployment, compression, and runtime environments
• Analyze and adapt ML models to improve compatibility and efficiency on compute-in-memory hardware and software
• Support software design, development, and performance profiling
• Collaborate with AI researchers and hardware engineers to validate system-level functionality
• Participate in code reviews, testing, and documentation

Skills

Python

C++

Data structures

Algorithms

Software architecture

TensorFlow

PyTorch

Education

Bachelor's degree in Computer Science, Electrical Engineering, or related field

Job description

TetraMem invites a Software Intern to contribute to tools, frameworks, and applications enabling neural networks on our novel analog compute-in-memory chips. This internship sits at the intersection of software, hardware, and AI.

You will develop and optimize Python or C++ code for model compression, deployment, and runtime environments, and adapt ML models to improve efficiency on compute-in-memory hardware.