WithCoverage raises $50M, led by Sequoia & Khosla

Engineering at WithCoverage

Artificial Intelligence to Protect the Real World

We build systems that handle tedious, repetitive work—so our team can do what AI can’t. You’ll work closely with the people who use what you build daily, and ship software that affects thousands of real businesses with real problems.

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.

live
PRs merged / wk
1130
median time to merge
49m
AI calls / wk
410k
AI tokens / wk
6.2B

Yesterday

Attachment writes preserve concurrent edits with version checks and idempotent retries

platform

50 API routes run on Nest with upload grants valid across deploys and rollbacks

platform

Fri · Nov 20

Isolated test databases enable parallel workers — median shard time drops from 331s to 194s

infra

Central access grants drive SSO and bounded organization membership sync

infra

Typed REST APIs unify app and tooling access; GraphQL runtime and codegen retired

platform

Per-worker database clones parallelize integration tests; median shard runtime down 41%

infra

Prefetched claims views switch in under 100 ms with deferred secondary reads

product

Thu · Nov 19

Targeted MongoDB indexes and selective recomputation reduce query and analytics work

infra

Idempotent migration jobs preserve IDs and audit writes across service boundaries

infra

Database workloads use targeted indexes and selective analytics recomputation

infra

Search facets compute cross-filter counts in a single aggregate query

platform

Live sandbox browser views use per-run watch-only tokens and scoped network access

infra

Wed · Nov 18

Cross-service record merges commit locally and reconcile linked records asynchronously

platform

Analytics runs on Kubernetes and managed Postgres with SSO and scoped script access

infra

Generated REST clients use shared service logic and batched, opt-in reads

platform

Typed REST APIs pair shared domain services with batched reads and generated clients

platform

Analytics runs on Kubernetes with managed Postgres and scoped browser and CLI access

infra

External lookups coordinate fleet-wide rate limits and shared backoff

platform

Tue · Nov 17

Cross-account backups pair immutable retention with verified restore drills

infra

Relationship-based authorization centralizes staff grants and workload scopes

platform

Worker pools rebalance capacity across concurrent enrichment jobs

infra

Cross-account storage replicas pair 35-day retention locks with verified restores

infra

Staff access and routing resolve through a shared authorization graph

platform

Mon · Nov 16

Record consolidation uses durable plans, resumable writes and version checks

platform

Aggregated thread reads replace up to 104 calls with one compressed response

platform

Batched relation reads make pipeline queries 25–35% faster

infra

Batched relational reads make pipeline queries 25–35% faster

infra

One paginated thread read replaces up to 104 API calls

platform

Sun · Nov 15

Copy-on-write database clones scrub staging data before network access

infra

Cross-account copy-on-write database clones power staging refreshes

infra

Why this job exists

Engineering is suddenlyvery 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.

Cole S.Mitch R.Nick O.Taylor A.

engineering

Cole S.
What are you building?
Both the brokerage and the system that runs it — an autonomous risk-analysis platform that takes the manual work off our experts so they stay on the judgment.
Where does your time go?
Mostly leverage: unblocking engineers, writing specs, making the hard technical calls — and building with AI agents myself.
What was hard to get right?
An architecture AI agents can actually build in. Keeping the system clean and consistent enough that an agent, not just a person, can ship real work is the hard part.
Why did you join?
A massive legacy industry barely touched by modern software — and the chance to go deep on a new domain and build it from the ground up.

Leadership

Who you'll build with.

  • JD Ross

    JD Ross

    Co-founder

    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.

  • Naveen Kasthuri

    Naveen Kasthuri

    CTO

    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.

Backed by Sequoia & Khosla · Series B

How we hire

A process builtto respect your time.

  1. Technical Deep Dive

    precision and depth

    We go deep on the decisions, the tradeoffs, and what you'd do differently. No trivia, no whiteboard puzzles.

  2. Coding Round with AI

    how you steer the model

    Bring 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.

  3. Onsite — 2–3 Interviews

    systems and product judgment

    A few focused sessions on systems design and product thinking. Architect something real, then reason about what to build, for whom, and why.

Do what AI can't. Build what it can.

View open roles