Remote AI Inference Engineer - Edge & On-Device Systems

Jobgether; Israel Township (OH); On-site; USD 93,000 - 179,000; Full time

Benefits offered by this job

Fully remote

Cutting-edge AI

High ownership

Collaboration with AI/fintech talent

Dynamic, fast-paced environment

Exposure to advanced AI frameworks

Competitive compensation

Job summary

Jobgether, posting on behalf of a partner company, seeks an AI Inference Engineer QVAC in Israel. You’ll work at the cutting edge of on-device AI, building runtime layers for fast, private inference on real-world hardware, near the metal, with low-level optimization and architecture.

You’ll design and optimize inference on edge devices, exploit llama.cpp/ggml/ONNX, improve memory and latency, and collaborate with researchers to move models to production, shaping decentralized AI experiences.

Qualifications

• Strong foundation in systems programming and ML concepts.
• Experience with AI inference on edge devices or constrained environments.
• Ability to learn new technologies quickly.

Responsibilities

• Design, optimize, and maintain the edge AI inference layer.
• Develop and optimize C++-based inference systems for edge devices.
• Enhance inference engines such as llama.cpp, ggml, and ONNX for performance.

Skills

C++

JavaScript

Deep learning

Edge deployment

Education

Bachelor's degree in Computer Science or related field

Tools

llama.cpp

ggml

ONNX

Job description

Jobgether, posting on behalf of a partner company, seeks an AI Inference Engineer QVAC in Israel. You’ll work at the cutting edge of on-device AI, building runtime layers for fast, private inference on real-world hardware, near the metal, with low-level optimization and architecture.

You’ll design and optimize inference on edge devices, exploit llama.cpp/ggml/ONNX, improve memory and latency, and collaborate with researchers to move models to production, shaping decentralized AI experiences.