AI Infrastructure Engineer: Real-Time Vision & LLMs

Ambient.ai; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Stock options

Health + welfare package

Flexible time off

Job summary

Ambient.ai is seeking an infrastructure-focused engineer to design, build, and optimize AI systems powering real-time security intelligence. You will work on scalable pipelines for video data, production ML models, and multimodal AI across enterprise environments.

Join a team collaborating with researchers and product teams to advance AI capabilities, improve latency and cost efficiency, and deliver reliable security outcomes from Redwood City–area offices in a hybrid work model.

Qualifications

• BS/MS in Computer Science or a related field.
• Strong Python development and software engineering fundamentals.
• Production experience with DL models including LLMs/LVMs or multimodal models.
• Experience with model-serving frameworks and evaluation pipelines.
• Cloud, containers, orchestration, and GPU-based workloads familiarity.

Responsibilities

• Design, build, and maintain AI infrastructure for real-time computer vision, LLM, LVM, and multimodal inference workloads.
• Scale systems to process large volumes of video and sensor data.
• Optimize inference latency, throughput, GPU utilization, reliability, and cost.
• Develop evaluation harnesses and benchmarking systems for model quality and production readiness.
• Build deployment pipelines for continuous model evaluation and deployment.
• Collaborate with research scientists to productionize latest AI advances.
• Improve model-serving architecture with batching, caching, routing, and quantization.
• Create observability, monitoring, and debugging tools for production AI systems.
• Define best practices for deploying AI in enterprise environments.

Skills

Python

Distributed systems

Production ML systems

LLMs/LVMs inference

Evaluation frameworks

Education

BS/MS in Computer Science or related field

Tools

vLLM

Triton Inference Server

CUDA/NCCL

PyTorch

Job description

Ambient.ai is seeking an infrastructure-focused engineer to design, build, and optimize AI systems powering real-time security intelligence. You will work on scalable pipelines for video data, production ML models, and multimodal AI across enterprise environments.

Join a team collaborating with researchers and product teams to advance AI capabilities, improve latency and cost efficiency, and deliver reliable security outcomes from Redwood City–area offices in a hybrid work model.