Artificial Intelligence Compiler Engineer at EnCharge AI

At EnCharge AI we design next-generation Edge AI chips that bring powerful inference directly to devices. Our team is growing quickly, and we are looking for experienced engineers who want to shape the software that makes these chips perform at their best.

What is this role?

This is a full-time, on-site position for a Senior Artificial Intelligence Compiler Engineer based in the United States. The role focuses on building and refining the compiler infrastructure that turns AI models into efficient code for our custom hardware.

What will you do?

• Design and implement key compiler components such as front-end graph optimizations, hardware-aware passes, back-end code generation, and low-level kernel libraries.
• Apply performance-driven methods to identify and deliver the optimizations needed for high-speed AI inference on edge devices.
• Partner with architecture, algorithms, runtime, and FPGA teams to co-optimize the full stack and deliver end-to-end performance gains.

What makes you a great fit?

We are looking for someone with a Master’s or Ph.D. in electrical engineering or computer science and more than five years of hands-on experience building compilers or chip architectures, ideally for AI accelerators. You bring strong proficiency in C++, Python, and systems programming, along with a solid track record in compiler or library design. Familiarity with LLVM, MLIR, TVM, and the graph formats used in modern toolchains is important, as is practical experience with TensorFlow and PyTorch. You understand how AI workloads behave and where performance bottlenecks occur, and you communicate technical ideas clearly in both speech and writing. Experience with CI/CD pipelines and knowledge of complete AI runtime stacks are viewed as valuable additions.

What's in it for you?

You will join a focused team working at the intersection of hardware and software to push the limits of edge AI. The work directly influences both our chip designs and the software that runs on them, giving you the opportunity to see your contributions deployed in real products.