Senior Software Engineer, GPU Code Generation for Machine Learning Inference

Ladders; United States; Remote; USD 152,000 - 288,000; Full time

Benefits offered by this job

Leading engineers

Generative AI inference

Collaborative environment

Job summary

The Ladders seeks a Senior Software Engineer specializing in GPU code generation for ML inference. You will design and optimize compiler/runtime techniques with hardware and AI specialists to improve speed, correctness, and scalability.

This remote role emphasizes strong C++ and Python development for tooling and performance analysis, profiling workloads, and contributing to cutting-edge generative AI inference workloads.

Qualifications

• BS, MS, or PhD in CS/CE or related, or equivalent experience.
• 4+ years of relevant software development experience
• Strong proficiency in C++
• Understanding of GPU architecture and parallel programming concepts
• Rigorous approach to performance analysis and debugging with a focus on numerical correctness
• Strong problem-solving and communication skills, with the ability to work independently and collaboratively

Responsibilities

• Design and implement efficient GPU code generation techniques for machine learning inference
• Develop compiler optimizations such as operator fusion and dynamic scheduling
• Profile workloads and analyze GPU code to identify bottlenecks
• Develop maintainable software in C++ and Python for tooling and performance analysis
• Collaborate with GPU architects and deep learning experts to guide design

Skills

C++ proficiency

GPU architecture knowledge

Performance analysis

Communication

Independent work

Python

Education

BS/MS/PhD in CS/CE or related

Job description

For our client, we are seeking a Senior Software Engineer, GPU Code Generation for Machine Learning Inference to join the team of a leader in the Telecommunications & Hardware space.

In this role, you will design and optimize GPU code generation capabilities that accelerate machine learning inference workloads. You will work on performance-critical compiler and runtime techniques that improve efficiency, numerical correctness, and scalability for advanced AI applications. This position partners closely with hardware architects and deep learning specialists to turn complex compute requirements into fast, maintainable software.

Location: Remote

Compensation: $152,000 - $287,500 annually

Responsibilities

• Design and implement efficient GPU code generation techniques for machine learning inference
• Develop compiler optimizations such as operator fusion and dynamic scheduling
• Profile workloads and analyze GPU code to identify bottlenecks
• Develop maintainable software in C++ and Python for tooling and performance analysis
• Collaborate with GPU architects and deep learning experts to guide design

Qualifications

• BS, MS, or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience
• 4+ years of relevant software development experience with substantial code contributions
• Strong proficiency in C++ and experience with performance-critical software
• Understanding of GPU architecture and parallel programming concepts
• Rigorous approach to performance analysis and debugging with a focus on numerical correctness
• Strong problem-solving and communication skills, with the ability to work independently and collaboratively

Benefits

• Work with leading engineers across GPU architecture and AI software
• Opportunity to solve demanding performance problems in generative AI inference
• Engage in a collaborative environment that values curiosity and innovation

Our client is an equal opportunity employer. We encourage you to apply even if you do not meet every qualification - your background could be exactly what this team needs.