AI Infrastructure Engineer (AI)

TL;DR

AI Infrastructure Engineer (AI): Designing and optimizing AI infrastructure for a real-time intelligence platform with an accent on large-scale inference for CV, LLM, and multimodal models. Focus on maximizing GPU utilization, reducing latency, and building robust evaluation harnesses for production AI systems.

Location: Hybrid in Redwood City, CA (must work from office 3 days a week)

Salary: $168,000 – $205,000 + Equity

Company

hirify.global is a category leader in Agentic Physical Security, utilizing reasoning Vision-Language Models to unify monitoring and threat assessment for world-class enterprise customers.

What you will do

• Design and maintain cutting-edge AI infrastructure for real-time computer vision, LLM, LVM, and multimodal inference workloads.
• Optimize inference performance focusing on latency, throughput, GPU utilization, and cost.
• Develop robust evaluation harnesses and benchmarking systems to measure model quality and production readiness.
• Partner with research scientists to productionize advancements in RAG, multimodal AI, and computer vision.
• Improve model-serving architecture through batching, caching, routing, and quantization.
• Build data engines and feedback loops for collecting training data and continuously improving AI performance.

Requirements

• 4+ years of industry experience building infrastructure, distributed systems, or production AI platforms.
• Strong programming background in Python with solid software engineering fundamentals.
• Hands-on experience running deep learning models (LLMs, LVMs, multimodal) in production.
• Proficiency in inference optimization techniques (quantization, parallelism, memory optimization).
• Experience with model-serving frameworks such as vLLM or Triton Inference Server.
• Must be based in the Bay Area to support the hybrid office requirement in Redwood City.

Nice to have

• Experience with CUDA, NCCL, PyTorch, TensorRT, or ONNX.
• Background in real-time computer vision or video understanding systems.
• Knowledge of model compression, speculative decoding, or distillation.
• Experience with vector databases and RAG pipelines.

Culture & Benefits

• Equity and stock options for shared ownership in company growth.
• Comprehensive health package including medical, dental, vision, and life insurance.
• 401k plan and legal services.
• Flexible time off, including a company-wide Winter Break.
• High-end technical equipment and company swag.