Embedded & Firmware Engineering.
Firmware, connected-device software, and board bring-up — written to be tested, updated over the air, and maintained. We prove the firmware on real hardware, sign every update, and keep the fleet serviceable in the field for years.
What shows up in your repo.
Agent graph
Typed nodes, tool schemas, retry and fallback policy. Versioned like code.
agents/*.ts · dag.yamlEval harness
Golden sets, LLM-as-judge, regression runs on every PR.
evals/*.jsonl · ci.ymlObservability
Traces, token costs, hallucination rates, drift alarms. Wired to your stack.
otel · datadog · honeycombRunbook
What to do when a tool 500s, when latency spikes, when eval red-lines.
docs/runbook.mdFirmware that ships, connects, and updates safely.
Embedded work fails late and expensively — a field bug you cannot patch, a device that cannot be updated, a driver that only works on one board. We engineer for the whole lifecycle.
Firmware & RTOS
Bare-metal and RTOS firmware (FreeRTOS, Zephyr) on common MCUs and SoCs — interrupt-driven drivers, power management, and a test harness that runs without the hardware in the loop.
IoT & connectivity
Device-to-cloud over MQTT, BLE, or Wi-Fi, with provisioning, telemetry, and signed over-the-air (OTA) updates so a fleet can be fixed in the field, not recalled.
Board bring-up & drivers
Board support packages, device drivers, and embedded Linux integration — turning a new board into a system that boots, talks to its peripherals, and runs your application.
Built to maintain
Reproducible build and flash pipelines, versioned firmware images, and CI for embedded targets, so the next engineer can ship a change with confidence.
A pricing engine, rebuilt in six weeks.
One representative case. Read the full editorial walkthrough, including the deploy log and latency chart.
Rebuilding a pricing engine in six weeks.
Series C fintech · monolith → 4 services + gateway · 42 TB ledger migrated · zero downtime.
READ THE CASE →Six things finance + eng teams want answered.
Whichever is best for the job — Anthropic, OpenAI, Google, or open-weights on your infra. We write the graph so the model is a swappable dependency.
Only under your DPA and with your key-management. We run on your cloud account unless you explicitly ask us to host.
Eval harness runs nightly and on every PR. If a model update breaks a grader, we freeze and triage before rollout.
Yes — our router speaks the APIs your team already runs: Salesforce, Zendesk, Stripe, Snowflake, internal services. We write typed tool schemas.
A monthly retainer tied to eval runs + on-call. Typically 8–15% of the build fee, reviewed quarterly. No surprise hours.
You do, from day one. Repo is yours. We leave MIT-licensed helper libraries where we can reuse them across clients.