Michael Gifford-Santos

Applied AI engineer — agent infrastructure, real-time voice, distributed inference

Seattle, WA — relocating to the SF Bay Area

• hello@michaelgifford.com
• +1 408.599.2275
• michaelgifford.com
• github.com/mijkal
• linkedin.com/in/michaelgifford

Fifteen years full-stack, on teams and on my own. Engineer #8 at Center, growing with it past 100 people and taking the web team from two engineers to three scrum teams; then first engineering hire at a K-12 platform that reached six-figure weekly transaction volume on a team that never exceeded two engineers. The last two years I’ve been building and operating the AI systems most teams only prototype — inference, agent orchestration, real-time voice, mobile, billing, monitoring, incident response — with co-founders on product and go-to-market. I run what I build.

What I bring

• I ship AI into production, then operate it.A real-time voice agent live in the App Store and Google Play, with the retrieval layer behind it — OCR-and-web ingestion into Qdrant, reranking and reciprocal-rank fusion, hybrid vector + full-text search over Postgres. The agent fleet that builds my own work runs on infrastructure I wrote: sigil (open source) supervising the sessions, Drydock deciding what is allowed to run unattended.
• I design the thing too.Six years as a working designer before engineering. On every product below I owned the interface and the brand as well as the stack — which removes a hire and the translation layer between the two.
• I own money paths.Two production payments systems in different domains, plus three years building corporate card and expense infrastructure. Collections, failed charges, chargebacks, refunds, entitlements, make-whole tooling.
• I ship alone and it holds up.Apps live in the App Store and Google Play; ~15 deployed services with runbooks, monitoring and written postmortems. Two engineers sustained Ordo through multiple raises because of what we deliberately didn’t build.
• I’ve been both halves of a founding pair— CEO/GTM at Dodecki v1 with a technical co-founder who shipped, the engineering half at Ensembl (Trip Terrano) and WunderGuide (Iqbal Ashraf).

Selected systems

sigil

agent-session infrastructure · Go · open source (MIT), github.com/mijkal/sigil

Daemon that turns tmux into a supervised process manager for long-running AI agent sessions: observable, interruptible and auto-restoring after host crashes — with sigil-web, a browser client that attaches to any session from any device over HTTPS, so the fleet is reachable from wherever I am. Built because operating a fleet of coding agents surfaced failure modes no local harness handles.

Drydock

multi-agent operations platform · React / FastAPI / Postgres

Operator dashboard running an ~16-project portfolio of autonomous coding agents.

• HMAC-signed hook callbacks and provenance tainting — context from untrusted sources routes the work onto the human-approval path instead of running unattended.
• Human-gated proposal model, with a per-task usage ledger and rate-limit ceilings — agent cost control as a first-class part of the platform, not an afterthought.
• Built to survive host failure: agent sessions auto-restore; runaway workers are bounded by concurrency caps, host-pressure gating and per-host jails.

mycellm

distributed LLM inference network · Python / QUIC · open source (Apache-2.0), PyPI, iOS app · mycellm.ai

Aiming at a BitTorrent-style protocol for inference: pool heterogeneous hardware, contribute capacity, draw on it. What runs today is a QUIC overlay with NAT-friendly reverse connections — seeders dial out and the gateway routes inference back down the live session, because hole-punching does not survive symmetric NAT. Public, private and federated networks are all first-class — the BitTorrent parallel is the topology, not just the swarm. Hardware-agnostic: a node serves local weights or brokers any compatible API behind one interface.

• Continuous-batching prototype: 4.29× throughput at concurrency 32, single-stream latency unchanged — driving mlx-lm’s BatchGenerator directly rather than vendoring an existing wrapper; prior art (oMLX, Apache-2.0) credited in NOTICE.
• On-device iOS inference in a shipped app; routing and capability announcement across heterogeneous nodes.

Experience

Aug 2025–present

WunderGuide (JNSQ Labs) — Co-founder / CTO

Voice-first AI travel concierge, launched Hawai’i-first; live in the App Store and Google Play. Incubated inside Dodecki, spun out Aug 2025. Co-founded with Iqbal Ashraf, who leads go-to-market; we work the product together near-daily. Hands-on across engineering, product design, brand and print collateral, and infrastructure/ops.

• Production real-time voice agent. LiveKit concierge grounded in live itinerary, location, travel-time and weather context under a real-time latency budget — grounding freshness traded against turn latency explicitly.
• Built the reliability half that makes it a product rather than a demo: an authenticated RevenueCat → entitlement pipeline with server-side reconciliation, plus make-whole tooling for when money and entitlement disagree.
• Built the retrieval layer behind the concierge. PDFs, web pages, documents and scanned images (OCR) through chunking, dedupe and contextual enrichment into Qdrant; query expansion, reranking and reciprocal-rank fusion on the way out; exposed as agent tools so text and voice share one knowledge base. Plus hybrid search over deals and business profiles in Postgres — vector + full-text + rating + recency — so the agent can tell a strong semantic match from a weak one.
• One product across native, embed and web: an affiliate-attribution system (probabilistic fingerprint + install-referrer), a partner portal for hospitality operators, an embeddable widget, and a web client mirroring the React Native app.

Sep 2021–Oct 2024

Ordo — Founding Software Engineer (first engineering hire)

K-12 food-service platform; Accel- and XYZ Venture Capital-backed. Joined at seed with one live school and one signed; sole engineer for roughly the first year, one of two after that, in a ~10-person company that grew to hundreds of schools across 15+ states.

• Delivered the MVP in under three months, replacing the founders’ Bubble prototype with the platform the company onboarded every school after the first onto.
• Built and owned the payments path — Stripe at six-figure weekly transaction volume, including collections, failed charges, chargebacks and refunds.
• Ran infrastructure, deploys and on-call solo, and onboarded the second engineer when engineering doubled.
• Shipped an iPad check-in kiosk, then followed real service. Larger lunchrooms ran on paper, so printed PDF report packs — sorted and grouped by roster and homeroom, matching how kitchens and front offices already worked — became the deliverable instead.
• Cut a per-meal student-name labeling step once live operations showed it added cost and labor with no service benefit.
• Built web, mobile and admin systems (React, React Native, Node.js, Hasura (GraphQL/Postgres), Stripe) and the support tooling a two-person team used to serve those hundreds of schools; a deliberate “v0.5” reporting stopgap held in production nearly three years before its v1.
• Front end stayed mine end to end; the backend moved Node → Rails as engineering became a pair.
• The founders drove the business model — local caterers and vendors — and a strong ed-tech salesperson turned it into contracts. I built what the model needed to run, through two further raises (Accel, then XYZ, cumulatively eight figures) on a team that never exceeded two engineers. Named at ordo.com/our-story; retained equity.

2020–present

Dodecki Labs — Founder / Product Engineer / Designer

Full-time since Oct 2024. The AI systems above are built and operated here — plus ~15 deployed services with runbooks, monitoring and written incident writeups across a k3s / Docker / Proxmox estate.

• I run a blend of coding agents in concert, not one. Claude, Codex and others are put on the same problem deliberately — to get consensus where it matters and genuinely different reads where it doesn’t. Knowing which model to hand a problem to, and when disagreement between them is the signal, is its own skill.
• GentlePrep — clinical-prep companion, iOS + Android. Shipped and operated solo, store ops included — and making sales on SEO/ASO alone, with no marketing spend.
• Ensembl (Sep 2020–Sep 2021) — real-time meeting assistant on self-hosted Jitsi/WebRTC, co-founded with Trip Terrano on the business side while I led engineering and owned full technical execution from first commit to production. React web, React Native iOS + Android, Firebase, Stripe. IP retained — and the real-time media foundation the voice-agent work later stood on.

2017–2020

Center — Senior Software Engineer, CenterCard · acquired by American Express (Apr 2025)

Joined as software engineer #8; left at 100+ employees. Corporate card and expense platform where correctness and reconciliation were the product.

• Built and owned major features end to end: async jobs, delegation, inbox, custom workflows.
• Grew the web team from 2 engineers to 3 scrum teams; led onboarding for every new web engineer through that scaling.
• Maintained the internal React component system; led cross-team code and design reviews.

2012–2017

Dodecki Software — Founder & CEO

Food ordering and delivery for Hawai’i restaurants — my first venture, and the one where I was the business half.

• Founder and CEO alongside a technical co-founder who led engineering: I raised capital, recruited the team, designed the product, and ran merchant onboarding and daily ops.
• Wound down — and it is why everything since ships with a runbook. Founder Institute, 2013.

---

Technical

Education

BA, University of Oklahoma · Design, University of Hertfordshire, UK · Founder Institute, Honolulu, 2013