Remote Edge AI/ML Engineer for Real-Time Vision & Robotics

Latent AI; Washington (District of Columbia); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Health, vision & dental benefits

401(k) plan

Remote/hybrid friendly

Job summary

Latent AI is seeking an AI/ML Engineer to push real-time computer vision models onto edge hardware for robotic and autonomous systems. You will design, train, and deploy production-grade ML systems with ultra-low latency.

The role emphasizes inference optimization, edge deployments, and integration with robotics platforms, using PyTorch, CUDA, TensorRT, Docker, and Kubernetes. Join us if you’re passionate about smarter robots and edge AI.

Qualifications

• Proficient in Python and modern ML frameworks (PyTorch).
• Strong background in computer vision and robotics.
• Experience deploying ML models on edge hardware with low latency.

Responsibilities

• Design, train, and deploy real-time computer vision models for edge devices.
• Optimize inference speed using CUDA and TensorRT on edge hardware.
• Integrate models into edge robotics platforms and ensure robust deployments.
• Manage containerized edge deployments with Docker and Kubernetes.
• Drive performance engineering to improve accuracy and efficiency in high-speed environments.

Skills

Python

Computer Vision

Robotics

Deep Learning

CUDA

Tools

PyTorch

TensorRT

Docker

Kubernetes

CI/CD

Job description

Latent AI is seeking an AI/ML Engineer to push real-time computer vision models onto edge hardware for robotic and autonomous systems. You will design, train, and deploy production-grade ML systems with ultra-low latency.

The role emphasizes inference optimization, edge deployments, and integration with robotics platforms, using PyTorch, CUDA, TensorRT, Docker, and Kubernetes. Join us if you’re passionate about smarter robots and edge AI.