Edge AI Engineer: Own End-to-End Customer Deployments

quadric technologies; Burlingame (CA); On-site; USD 170,000 - 230,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

Equity

Paid Parental Leave

401(k) Retirement Plan

Flexible PTO

Catered lunch

Downtown Burlingame office

Collaborative culture

Caltrain nearby

Job summary

Quadric in Burlingame, CA is seeking a hands-on, technically focused engineer to own the design-win path for the Chimera GPNPU, spanning quantization, custom kernels, and compiler work. You will engage with customers to move workloads to target latency and accuracy, port workloads, and craft kernel solutions.

You will work on-site and remotely with customer engineering teams to debug issues, drive evaluations, and shape the roadmap while codifying learnings into reusable SDKs and playbooks.

Qualifications

• Strong C++ and Python with performance-critical code for constrained targets.
• Systems-level performance intuition: memory bandwidth and profiling.
• High agency and independent problem-solving; empirical, not theoretical.
• Comfortable operating without a playbook in ambiguity.

Responsibilities

• Convert 2-3 active customer evaluations into committed design wins by getting customer workloads running at target latency and accuracy on Chimera.
• Port customer workloads onto Chimera - architect, adapt, profile, and write custom kernels when required.
• Work on-site and remotely with customer engineering teams: debug failures, hit benchmark targets, and guide model-architecture tradeoffs.
• Drive evaluations forward end-to-end, from first technical conversation through design win.
• Codify what you learn into reusable assets - SDK skills, porting playbooks, and agentic content - so each subsequent engagement moves faster than the last.
• Build applications and benchmark collateral that support future customer engagements.
• Partner with engineering and product teams to relay customer learnings and shape the roadmap.
• Contribute skills and playbooks to Quadric's growing agentic FDE toolset.

Skills

C++

Python

Perf optimization

System-level

Job description

Quadric in Burlingame, CA is seeking a hands-on, technically focused engineer to own the design-win path for the Chimera GPNPU, spanning quantization, custom kernels, and compiler work. You will engage with customers to move workloads to target latency and accuracy, port workloads, and craft kernel solutions.

You will work on-site and remotely with customer engineering teams to debug issues, drive evaluations, and shape the roadmap while codifying learnings into reusable SDKs and playbooks.