AI today is trapped in the hands of the GPU cartel — locked in costly servers, paywalled clouds, and data-hungry monopolies. At ZETIC.ai, we are breaking those chains.

Our platform, MLange, is the world’s first universal on-device AI deployment engine. It lets developers run any AI model, on any hardware, 100x faster — no GPU clusters, no cloud bills, no data leaks. With 5+ billion smartphones, tablets, and edge devices as the new infrastructure, we’re unleashing the sleeping giant of AI.

We exist to give every developer, startup, and nation AI Freedom:
• Zero dependency on GPU clouds
• Zero infra cost
• Zero compromise on privacy
• Runs everywhere, offline, instantly

We’re not here to play it safe. We’re here to flip the rules of AI.

We’re looking for a Senior ML Software Engineer ready to take on hard problems and build the backbone of AI Freedom. This is not a “maintenance” role — it’s a chance to design, optimize, and scale the runtime that will power billions of devices worldwide.

If you thrive at the intersection of AI frameworks, system software, and mobile/embedded platforms, and you want your work to break the status quo, this is your calling.

What You’ll Do

• Architect and optimize runtime components in C++ and Python
• Deploy AI models on mobile/embedded targets with a laser focus on performance and reliability
• Collaborate with global AI researchers to bring state-of-the-art models into real-world apps
• Improve SDK usability so developers can ship AI apps effortlessly
• Push the limits of benchmarking, profiling, and hardware acceleration across NPUs/GPUs/CPUs

What We’re Looking For

• Strong proficiency in C/C++ and Python
• Proven experience in system software or runtime/infra development
• Hands-on track record of deploying AI models into real-world devices/services
• Familiarity with mobile (Android/iOS) or embedded systems
• Experience with model runtimes (ONNX Runtime, TensorRT, CoreML, TFLite, LiteRT etc.) is a plus
• Deep understanding of performance profiling, memory optimization, hardware acceleration

Bonus Points

• Built or contributed to cross-platform runtimes or SDKs
• Experience with heterogeneous hardware acceleration (NPU/GPU/CPU)
• Previous work in AI infrastructure, edge AI, or model optimization