Software Engineer – AI Inference Engine

FriendliAI San Mateo, CA $160,000 - $230,000
Full Time Mid Level 5+ years

Posted 3 weeks ago

Interested in this position?

Upload your resume and we'll match you with this and other relevant opportunities.

Upload Your Resume

About This Role

Optimize the performance and efficiency of FriendliAI's core AI inference engine. This role involves designing, implementing, and optimizing GPU kernels and supporting infrastructure for next-generation generative and agentic AI workloads, directly powering latency-critical and compute-intensive systems.

Responsibilities

  • Design and optimize custom GPU kernels for AI (e.g., transformer and diffusion) workloads
  • Contribute to the development of FriendliAI’s kernel compiler, memory planner, runtime, and other core components
  • Collaborate with cloud and infrastructure engineers to ensure end-to-end inference performance
  • Analyze performance bottlenecks across the software and hardware stack, and implement targeted optimizations
  • Drive support for new model architectures and tensor compute patterns
  • Maintain production-grade performance infrastructure, including profiling, benchmarking, and validation tools

Requirements

  • 5+ years of experience in production or high-impact research environments
  • Production-level expertise in Python and C++
  • Bachelor’s or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent
  • Experience developing machine learning frameworks or performance-critical runtime systems
  • Hands-on experience writing and optimizing GPU kernels
  • Hands-on experience profiling GPU kernels
  • Experience working with generative AI models such as transformer and diffusion models

Qualifications

  • Bachelor’s or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent
  • 5+ years of experience in production or high-impact research environments

Nice to Have

  • Experience developing machine learning compilers or code generation systems
  • Familiarity with dynamic shape compilation, memory planning, and kernel fusion
  • Contributions to inference engines, compilers, or high-performance numerical libraries
  • Understanding of multi-GPU and distributed inference strategies

Skills

Python * C++ * Diffusion models * GPU programming * Transformer models *

* Required skills

Benefits

Health Insurance
Daily lunch
Health check-up support
Startup equity
Flexible working hours
Daily dinner
Top-tier equipment support
Competitive compensation
Unlimited snacks and beverages

About FriendliAI

FriendliAI is a Redwood City, CA-based startup building the next-generation AI inference platform that accelerates the deployment of large language and multimodal models with unmatched performance and efficiency.

Technology
View all jobs at FriendliAI →