engineering / withcoverage
Build the services brain
We encode the judgment behind corporate risk decisions into models that run in the critical path. Insurance is just where we start.
- role
- member of technical staff
- stack
- aws, vercel, eks, argocd, postgres, iceberg
- ai
- custom-built harnesses, autonomous coding, self-improving loops
- where
- nyc, in office, five days
// changelog
Recent production changes.
- PRs merged / wk
- 232
- median time to merge
- 22m
- AI calls / wk
- 398k
- AI tokens / wk
- 5.3B
Today
Sandboxed automation runners isolated on Spot-only ARC capacity
infraDurable reconciliation and bounded polling for 100+ row bulk certificate runs
platformWorkflow observability canvas links live activity stats to trace history
platformMobile video playback pauses offscreen work to reduce device load
productYesterday
Warm replica pool sized for bursty bulk certificate workloads
infraDeterministic inbox drain semantics for dependent conversation metadata
platformWarm replica pool sized for bulk certificate workloads with bounded DB pressure
infraFri · Aug 21
Serialized billing orchestration with idempotent provider-write boundaries
platformResumable communications archive import handles split batches and parent worklists
infraCommunication mirror retry policy classifies terminal writes and stable alerts
infraCommunication read APIs typed end to end with generated contract coverage
platformEmail sign-in codes backed by bounded attempts and additive token state
infraArchive loader tracks resumable repair worklists across split export batches
infraCommunication mirror uses row-level classification for edge-denied writes
infraThu · Aug 20
Encrypted communication archive codified with scoped loader identity and retention
infraResumable communication archive loader validates batches before insert-only import
platformCurrent policy billing projection split into workflow, storage, and batch API
platformCollaborative draft writes flow through synchronized editor transactions
platformDedicated export archive codified with KMS, access logs, and ephemeral loader identity
infraLarge workflow inputs moved to immutable activity references below orchestration limits
infraCollaborative draft writes use transactional editor state with stale-write guards
platformWed · Aug 19
Type-aware linting runs 7-11x faster across app and backend
platformService-backed conversation reads shipped with fallback and comparison telemetry
platformCommunication mirror stores account identities, inbox memberships, and delivery state
infraCommunication mirror expanded for internal comments, accounts, handles, and bounces
platformEntity-access assignments updated atomically with bulk scope replacement
platformTue · Aug 18
Communication servicing workers launched with scoped credentials and schema grants
infraAccount-entity APIs wired with service-only permissions and idempotent writes
platformCommunication mirror replay keyed by dependency digests for convergent retries
infraMarketing media pipeline optimized with responsive video and deferred loading
infra// why_this_job_exists
Engineering is suddenly very different
Companies used to hire people to fuel growth and pay SaaS vendors for software they could use. That's all changed — now companies want to buy outcomes.
Our team builds the platform and tools to enable our risk management experts to scale themselves 2x, 10x, or 100x more than was possible in the past.
We are working to break the scaling laws of services businesses with AI agents. We are a deeply collaborative, in office, hard working and curious team in NYC.
Diagram: AI agents pull insurance documents from a task queue, work them concurrently, and ship finished artifacts without supervision. Interactive: choose a file in the queue to dispatch it to an idle agent, select an agent to see its live log, or select a shipped artifact to preview it.
Diagram: an engineer and a risk expert deploy as a pair into client verticals — defense, hospitality, logistics, energy — build on site, and ship measurable outcomes. Interactive: choose a site to deploy the pair there, or select a deployed site for details.
Diagram: an AI harness loops through run, eval, learn, and update stations. Each lap appends an improvement to the harness changelog, evals flip from fail to pass, and the pass rate climbs from 62 to 94 percent. Interactive: select the next station to drive an iteration by hand, or any station for details.
Diagram: a fleet of AI agents serves a growing wall of client accounts, routing only rare judgment calls to a single risk expert. Accounts per expert climbs from 10 to 100. Interactive: choose an unlit account tile to onboard it, or select the expert or an agent for details.
Real, interesting problems — You'll build AI infrastructure that can read and understand complex documents, ask questions, make decisions, and take actions that have real consequences for our clients' businesses. You'll learn what it takes to build and deploy autonomous agents that manage risk at scale in the real world.
// inside_the_team
The actual work
- What are you building?
- An AI-driven claims platform that gives clients full visibility into their claims, losses, and legal processes — turning messy insurance data into something clear.
- Where does your time go?
- Deep dives into a problem, designing the system, shipping it, then iterating fast with the people who use it. One day I'm evaluating the latest AI, the next I'm shipping what the team uses tomorrow.
- What was hard to get right?
- Nuance. Insurance is a language-based industry — every policy is specific to the client and their business, and one small detail flips the answer. Building repeatable systems on that takes real domain depth.
- Why did you join?
- The team, and how embedded we are with our users. I get to shape the product next to the people using it and watch the impact land in real time.
// who_you_build_with
Who you'll build with.
An entrepreneur and product leader with a track record of building category-defining companies. He co-founded Opendoor, taking it from inception through IPO, and brings a product-first instinct to everything we build.
A pioneer in AI-native engineering with a background that blends finance and technology. Previously a senior principal engineer and chief architect in charge of transforming a 700-person R&D org to be AI-native.
// how_we_hire
A process built to respect your time.
- 01
Technical Deep Dive
→ precision and depthWe go deep on the decisions, the tradeoffs, and what you'd do differently. No trivia, no whiteboard puzzles.
- 02
Coding Round with AI
→ how you steer the modelBring your own AI tooling and pair on a real problem. We don't ban the model or treat it as cheating — using it well is the job. We watch how you prompt, review, debug, and steer it, because that's exactly how you'll ship here.
- 03
Onsite — 2–3 Interviews
→ systems and product judgmentA few focused sessions on systems design and product thinking. Architect something real, then reason about what to build, for whom, and why.
// join_us
Work where the model has to be right.
Interested? We’re always looking for talented problem-solvers to join our team.