Forward Deployed Engineer

Job Title

Forward Deployed Engineer

Role Summary

Field-facing engineer who owns the technical path from customer evaluation to silicon design for the Quadric Chimera GPNPU. Work across the full stack-quantization, custom kernels, compiler tooling-and embed with customer engineering teams to port and optimize workloads for edge devices.

Capture and codify learnings into reusable SDK skills, porting playbooks, and agentic tooling to accelerate future engagements.

Experience Level

Mid-level. The posting does not specify a required number of years of experience.

Responsibilities

Primary responsibilities focus on driving technical evaluations to design wins and enabling customers to ship on Chimera.

• Convert customer evaluations into committed design wins by meeting target latency and accuracy on Chimera.
• Port, profile, and optimize customer workloads; design and implement custom kernels when required.
• Embed with customer engineering teams on-site and remotely to debug failures, hit benchmarks, and guide model/architecture trade-offs.
• Manage evaluations end-to-end from first technical conversation through design-win delivery.
• Develop reusable assets: SDK skills, porting playbooks, benchmark collateral, and agentic FDE content.
• Partner with product and engineering teams to relay customer feedback and influence the product roadmap.

Requirements

Key must-have skills and preferred background.

• Must-have: Strong C++ and Python; experience writing performance-critical code for constrained targets (DSP, NPU, GPU, or embedded SoC).
• Must-have: Systems-level performance intuition (memory bandwidth, data movement, cycle-level reasoning) and ability to read and act on profiles.
• Must-have: High agency, independent problem-solving, and comfort operating without established playbooks in ambiguous situations.
• Preferred: Prior FAE, Sales Engineering, FDE, or startup experience owning end-to-end implementations.
• Preferred: Background at NPU/edge-AI IP, silicon companies, inference-focused startups, kernel optimization teams, or similar low-latency engineering roles.
• Preferred: Familiarity with or strong interest in agentic developer tooling (e.g., Claude Code).

Education Requirements

Not specified.

About the Company

Company: Quadric

Headquarters: Burlingame, California, United States

Quadric is building the world’s first supercomputer designed for the real-time needs of edge devices. Founded in 2016, the company empowers developers across industries with innovative general-purpose neural processing unit (GPNPU) architecture for neural network workloads. Co-founded by technologists from MIT and Carnegie Mellon, Quadric aims to enable groundbreaking technology development.