1 day ago
Responsibilities
- Own and manage a physical partner device lab containing SoCs from Qualcomm, AMD, Intel, NVIDIA, and other edge-chip vendors.
- Lower Liquid Foundation Models onto partner silicon and profile speed, latency, throughput, power, and thermal performance.
- Create a repeatable profiling process and benchmark new chipsets within weeks of arrival.
- Work with partner customer engineers and OEM stakeholders to co-create demos and benchmark narratives.
- Present technical results to partners and demand-side buyers, explaining comparative LFM performance.
- Diagnose model and runtime performance gaps at the hardware level and communicate actionable findings to the Edge Inference team.
- Contribute to runtime and model-level optimization when qualified.
Requirements
- Demonstrated experience deploying and profiling ML models on at least one edge SoC family, such as Qualcomm Snapdragon/Hexagon, AMD Ryzen AI/XDNA, Intel NPU, or SiMa.ai MLSoC.
- Working knowledge of at least one vendor lowering or runtime toolchain, such as Qualcomm AI Engine Direct/QNN, SiMa Palette, OpenVINO, or ONNX Runtime execution providers.
- Experience measuring on-device latency, throughput, power, and thermal performance.
- Ability to present technical results to external engineers and commercial stakeholders.
- Preferred: experience across two or more chipset families.
- Preferred: experience in chip-vendor customer engineering, field applications, or AI-enablement teams.
- Preferred: runtime or kernel-level optimization experience.
Benefits
- Competitive base salary with equity in a unicorn-stage company.
- 100% employer-paid medical, dental, and vision premiums for employees and dependents.
- 401(k) matching up to 4% of base pay.
- Unlimited paid time off and company-wide Refill Days.
- Role is based in Boston or San Francisco and is not remote because it requires ownership of physical hardware.
Categories
About Liquid AI
Liquid AI builds general-purpose AI systems that run efficiently from data center accelerators to on-device hardware, emphasizing low latency, memory efficiency, privacy, and reliability. The company partners with enterprises in consumer electronics, automotive, life sciences, and financial services to deploy and benchmark models for real-world workloads. Founded in 2023 out of MIT CSAIL and headquartered in Cambridge, Massachusetts, it is privately held.