E. Knuth

Sheet 01 — General arrangement · REV 2026.08

AI on the device. Systems that hold.

I am Edwin Knuth, a senior staff product engineer in Portland. I spent a decade on observability UI at New Relic, then two years owning the capture frontend of an FDA-cleared imaging product at Overjet. Now I build applications that run speech and vision models entirely on the phone in your pocket.

See the work Hire me

Open to senior staff and principal roles · Portland, OR · remote-friendly

Specification

Discipline
On-device AI · Product engineering · Observability
Grade
Senior staff / principal
Availability
Immediate · remote
ON-DEVICE AI ◆ OPENTELEMETRY ◆ FDA 510(K) ◆ WHISPER · ONNX · WHISPERKIT ◆ REACT · TYPESCRIPT ◆ SWIFT · KOTLIN · PYTHON · C# ◆ OBSERVABILITY ◆ OFFLINE-FIRST ◆ ON-DEVICE AI ◆ OPENTELEMETRY ◆ FDA 510(K) ◆ WHISPER · ONNX · WHISPERKIT ◆ REACT · TYPESCRIPT ◆ SWIFT · KOTLIN · PYTHON · C# ◆ OBSERVABILITY ◆ OFFLINE-FIRST ◆

Sheet 02 — Measured results

Numbers, taken off the drawing

Every figure below came out of shipped production work, not a slide. The context for each one is on the résumé sheet.

MEASURED IN PRODUCTION
510(k)

FDA cleared

K253930 — Iris imaging, capture frontend

99.5%

sessions finalized

capture completes through backend outages

0

clinics live

scaled up from a single pilot site

0

memory cut

on-device ASR, Android peak RSS

Sheet 03 — Selected work

Things I built to find out if they were possible

These are personal builds, not employer work, which is why I can show you the source. The shipped product engineering is on the résumé sheet; this is what I do when I want to find out whether something is possible.

DWG 001

Earshot

Open source

On-device speech-to-text SDK

One Kotlin core drives speech recognition on both iOS and Android. Whisper through WhisperKit on iOS, ONNX Runtime on Android. No audio leaves the phone.

  • Kotlin
  • Swift
  • WhisperKit
  • ONNX Runtime
  • KMP
peak memory cut
37% peak memory cut
WER vs 14.97% platform
8.38% WER vs 14.97% platform
platforms, one core
2 platforms, one core
Read the detail sheet → Source on GitHub
DWG 002

Pencil Count

Open source

Local vision pipeline over 406,769 ballots

A six-stage funnel that reads handwritten write-in votes off scanned ballot images using a 12B vision model running locally, and reconciles the tally against the official count.

  • Python
  • Local 12B VLM
  • OCR
  • Batch pipeline
ballots processed
406,769 ballots processed
variance vs official
1.4% variance vs official
pipeline stages
6 pipeline stages
Read the detail sheet → Source on GitHub
DWG 003

Sitewinder

Personal build

Retrieval chat over your own video, offline

An Android app that composes Whisper ASR, MiniLM embeddings, and Gemma 3 1B entirely on device, so you can ask questions about your own video library with the radio off.

  • Kotlin
  • Whisper
  • MiniLM
  • Gemma 3 1B
  • Vector search
models, one device
3 models, one device
network calls
0 network calls
Read the detail sheet →
All work sheets

Sheet 04 — Service record

Where the production scars came from

Mar 2024 — Aug 2026

Overjet

Senior Staff Software Engineer

Dental AI · Iris Intelligent Imaging System

  • Shipped the Iris capture frontend through FDA 510(k) clearance (K253930), the company’s first clearance in image capture and PACS.
  • Built offline-mode resilience so capture sessions finish through backend outages, driving a 99.5% session finalization rate. Converting the app to a PWA is what made it possible.
  • Scaled the capture product from one pilot clinic to 145 clinics.

Jan 2022 — Feb 2024

New Relic

Staff Software Engineer

Observability platform · Logging

  • Shipped two LLM-powered features in New Relic AI for Logging, error analysis on log lines and automatic generation of parsing expressions, in production for enterprise customers in 2023.
  • Rearchitected data fetching across Logging UI components to meet performance SLOs and cut query timeouts on large datasets.
Full résumé Download PDF → Six years of New Relic APM and Browser work also on that sheet

Sheet 05 — Scope of work

What I am looking for

  • 01 Senior staff or principal, on a team where the hard problem is real.
  • 02 Product engineering is the day job and always has been: the frontend of an FDA-cleared medical device, the UI of an observability platform used by enterprises. On-device AI is where I have been pushing since.
  • 03 On-device and edge AI, developer tools, or observability. Those are the three places my ten years of platform work and my last two years of on-device AI work meet.
  • 04 Remote, Portland-based. Comfortable being the person who owns the ugly reliability problem nobody has claimed.
Email me LinkedIn

eknuth@gmail.com