Member of Technical Staff - Partner Inference Engineer
Liquid AI is an efficiency-first foundation-model company building device-native Liquid Foundation Models (LFMs) and tools to customize and deploy them.
Funding history
About Liquid AI
An MIT CSAIL spinout, Liquid AI develops general-purpose AI models focused on efficient deployment across CPUs, GPUs, NPUs, edge devices, and cloud or on-premises environments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build and run the partner silicon program, including the device lab, profiling process, and technical relationships with partner engineering teams. You will deploy Liquid Foundation Models on edge hardware, measure performance, diagnose hardware-level gaps, collaborate on demos and benchmarks, and present results to partners and buyers.
Requirements
- Deploy and profile ML models on at least one edge SoC family
- Use at least one vendor lowering and runtime toolchain
- Measure on-device latency, throughput, power, and thermal performance
- Present technical results to external engineers and commercial stakeholders
Responsibilities
- Manage the partner device lab and partner-provided edge SoCs
- Lower Liquid Foundation Models onto partner silicon
- Profile model speed, latency, power, and thermal performance
- Co-create demos and benchmark narratives with partner customer engineers
- Present technical results to partners and demand-side buyers
- Diagnose model and runtime performance gaps for the Edge Inference team
- Contribute to runtime and model-level optimization where possible
Benefits
- Equity
- Medical, dental, and vision premiums covered for employees and dependents
- 401(k) matching up to 4% of base pay
- Unlimited PTO
- Company-wide Refill Days