Software Engineer, ML Platform (ML Serving)

TL;DR

Senior Software Engineer (ML Serving): Building and operating ML serving infrastructure for autonomous driving, scene understanding, and automated mapping with an accent on powering foundational models (LLMs & VLMs) and ensuring robust, efficient, and scalable ML model serving. Focus on designing and implementing GPU-accelerated inference systems and collaborating with ML researchers and data engineers to productionize cutting-edge AI innovations.

Location: Hybrid in Foster City, CA, USA

Salary: $189,000–$258,000 a year

Company

hirify.global is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem for mobility-as-a-service in urban environments.

What you will do

• Build off-vehicle inference services for Foundational models (LLMs & VLMs) and rider experience models.
• Lead the design, implementation, and operation of robust and efficient ML serving infrastructure.
• Collaborate with cross-functional ML, software, and data engineering teams on requirements and architecture.
• Provide technical guidance and mentorship to junior engineers.

Requirements

• 4+ years of ML model serving infrastructure experience.
• Experience building large-scale model serving with GPU and/or high QPS, low latency use cases.
• Experience with GPU-accelerated inference using RayServe, vLLM, TensorRT, Nvidia Triton, or PyTorch.
• Experience working with AWS and Kubernetes.

Culture & Benefits

• Comprehensive package including paid time off (sick, vacation, bereavement), unpaid time off, hirify.global Stock Appreciation Rights, and Amazon RSUs.
• Health insurance, long-term care, short-term and long-term disability, and life insurance.
• Opportunity to have a significant impact on autonomous robotaxi deployment.
• Commitment to diverse perspectives and building a team with varied backgrounds.