Lead Engineer - Compilers

Lead Engineer- AI Compilers

Our game-changing AI solutions revolutionize what people and businesses can achieve. Ara inference processors combined with our SDK deliver unrivaled deep learning performance at the edge to accelerate and optimize real-time decision making where every millisecond is critical, and power efficiency is a must.

This is what you are responsible for:

• Architect and implement high-impact compiler subsystems: IR design, lowering pipelines, operator fusion, scheduling, and target code generation for our NPU.
• Lead design and deployment of quantization flows, mixed-precision strategies, and numerical-correctness/bit-exactness verification.
• Implement and ship production-grade codegen and runtime integrations that are stable, debuggable and performant.
• Drive low-level optimizations and collaborate with kernel teams to close the HW/SW performance gap (including micro-kernel design and latency/throughput tradeoffs).
• Define and enforce best practices for compiler CI, performance regression suites, profiling, and release gating.
• Troubleshoot and root-cause complex performance or correctness issues on real customer models; produce reproducible fixes.
• Mentor senior/junior engineers, do design reviews, and raise the team's technical bar.
• Influence product and silicon roadmap by identifying compiler-driven feature opportunities and tradeoffs.
• Represent the company in technical engagements with customers and partners (deep integrations, POCs, performance characterizations).

Necessary Qualifications:

• Deep expertise in ML compilers and toolchains (MLIR, LLVM, TVM, XLA, Glow, or similar).
• Proven experience with graph lowering, IR design, operator fusion, scheduling, and target codegen for accelerators.
• Strong systems programming skills — expert C++ and solid Python for tooling and infra.
• Demonstrated track record of shipping production compiler components used in deployed products.
• Excellent debugging & profiling skills with performance toolchains (perf, custom profilers, trace analysis).
• Strong communication skills and experience working cross-functionally with hardware architects, kernel teams, and product.
• Passion for mentorship and improving engineering practices across teams.