About Positron AI

Positron.ai specializes in developing custom hardware systems to accelerate AI inference.  These inference systems offer significant performance and efficiency gains over traditional GPU-based systems, delivering advantages in both performance per dollar and performance per watt.  Positron exists to create the world's best AI inference systems.

Job Title: Software Engineer - LLM Inference Appliances & Customer Onboarding

 We are looking for skilled Software Engineers to join our team and help us deliver reliable, secure, and efficient solutions for our customers. This role involves debugging and resolving software issues, onboarding customer use cases, and ensuring smooth operations of LLM inference systems in production environments.

Responsibilities:

• Debugging and Issue Resolution:
• • Identify, debug, and resolve complex issues across the entire software stack (including system-level, application-level, and network issues).
  • Work with cross-functional teams to troubleshoot and address issues promptly, ensuring the smooth operation of systems in production.
  • Develop automated testing strategies and tools to prevent regressions and ensure the robustness of the software.
    
    
• Customer Onboarding and Model Management:
• • Work closely with customers to onboard their use cases onto our Linux-based LLM inference appliances.
  • Provide customers with the ability to select and activate different models on their devices, ensuring compatibility and ease of use.
  • Develop and implement features for loading new models onto devices, minimizing downtime and improving overall user experience.
    
    
• Patch Methodology and Device Management:
• • Develop and maintain a stable, efficient methodology for patching software on devices in production, ensuring smooth updates and minimal disruption.
  • Collect and manage detailed system and device performance data from production environments, identifying potential areas for improvement.
    
    
• Performance Diagnosis and Optimization:
• • Diagnose and resolve performance issues within the software stack, including inefficiencies related to hardware, models, and system configurations.
  • Collaborate with subject matter experts to analyze performance shortcomings and implement corrective measures to keep customer environments optimized and functional.
    
    
• Cross-Functional Collaboration:
• • Work closely with customer support, QA, and other engineering teams to ensure effective resolution of issues and continuous improvement of systems.
  • Assist in defining and implementing best practices for onboarding new customers and handling complex use cases.

Requirements:

• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent experience.
• Proven experience as a Software Engineer with a strong focus on debugging, customer use case onboarding, and managing Linux-based systems.
• Strong proficiency in programming languages such as Python, C++.
• Solid understanding of Linux systems, system administration, and infrastructure management.
• Experience with model management and loading systems, especially in environments with custom hardware or AI/LLM applications.
• Familiarity with automation tools and CI/CD pipelines.
• Excellent troubleshooting skills and the ability to analyze and resolve issues across a broad range of systems.
• Ability to collaborate with cross-functional teams and subject matter experts to resolve complex technical challenges.
• Strong communication skills, both written and verbal, with the ability to communicate effectively with customers and internal teams.

Preferred Qualifications:

• Experience with cloud platforms (e.g., AWS, Azure) or edge computing environments.
• Familiarity with AI/ML frameworks and tools (e.g., TensorFlow, PyTorch, Hugging Face).
• Experience in performance tuning and system optimization for large-scale applications or hardware-based systems.
• Knowledge of security best practices for embedded or Linux-based systems.

Why Join Us?

• Work on a cutting-edge ML inference platform that redefines performance and efficiency for LLMs.
• Tackle some of the most challenging low-level performance engineering problems in AI today.
• Collaborate with a team of hardware, software, and ML experts building an industry-first product.

Opportunity to contribute to and shape the future of open-source AI inference software.