New: upload your resume and get matched to AI jobs. Free to start →

Senior Software Engineer - Maia Model Enablement

$120k - $235k • United States, Multiple Locations, Multiple Locations • Full-time

Posted 16d ago

Job Location

United States, Multiple Locations, Multiple Locations

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

AI Infrastructure Engineer

About the job

The Maia Model Enablement team is responsible for the complete technical process of integrating advanced AI models onto Microsoft's AI accelerators and ensuring their successful deployment in production. This involves model integration, performance tuning, serving capabilities, validation infrastructure, hardware setup, and cross-system debugging. We are seeking a Senior Software Engineer who thrives on tackling complex, end-to-end system challenges at the intersection of AI models, software, and hardware. The ideal candidate possesses deep technical knowledge, strong systems thinking, and the ability to rapidly master new areas to drive significant production impact.

Responsibilities

  • Integrate new AI models and architectures into the Maia system.
  • Diagnose and resolve issues across software, systems, and hardware layers.
  • Enhance performance, scalability, and serving capabilities for AI workloads in production.
  • Develop automation, validation infrastructure, and engineering systems to expedite model onboarding.
  • Collaborate with model, runtime, infrastructure, and hardware teams to overcome obstacles and achieve production goals.
  • Ensure new model architectures function correctly on Maia.
  • Meet performance, scalability, and reliability targets for production models.
  • Identify and resolve bottlenecks across the entire technology stack.
  • Enable new hardware generations for use by model teams.
  • Streamline and improve the repeatability and operational efficiency of model onboarding.

Requirements

  • Bachelor's Degree in Computer Science or a related technical field, with 4+ years of technical engineering experience in languages like C++ or Python, or equivalent experience.
  • Understanding of modern AI model architectures, inference systems, and performance characteristics.
  • Experience with AI/ML frameworks, runtimes, or serving stacks such as PyTorch, ONNX Runtime, vLLM, TensorRT-LLM, or similar.
  • Experience diagnosing and resolving complex issues across software, systems, and hardware layers.
  • Familiarity with performance analysis, distributed systems, accelerator architectures, or large-scale production services.
  • Experience enabling software on new hardware platforms, accelerators, or large-scale systems through activities like bring-up, performance characterization, hardware-software debugging, or platform enablement.
  • Experience using AI-assisted engineering tools, agents, skills, and workflow automation for software development, debugging, code maintenance, investigation, and engineering productivity.
  • Proficiency in software development with languages such as Python, C++, or equivalent technologies.

Benefits

  • Annual base pay range: $119,800 - $234,700 (U.S. national average)
  • Annual base pay range: $160,200 - $261,000 (San Francisco Bay Area and New York City metropolitan area)
  • Eligibility for other benefits and compensation