Founding Engineer

A $200M solar project gets financed on the strength of a few thousand PDFs: ground leases, interconnection agreements, offtake contracts, permits, title. Analysts read them line by line, by the hour. The documents arrive out of order, in the wrong formats and scanned sideways. The term that kills the deal is on page 74 of a second amendment to an amendment. That review is the bottleneck between capital and megawatts on the grid.

BuildQ accelerates those projects. Our platform has processed 200,000+ documents across 1,100+ projects for the developers, IPPs and funds building multi-billion-dollar solar, wind and storage portfolios.

Most AI companies sell you a tool and wish you luck. We’ve moved to AI-native services. Our customers don’t just use BuildQ to run diligence; they order diligence from BuildQ. An agent builds the deal’s document set, extracts and cites the terms, drafts the site control and interconnection deep-dives, and assembles the IC memo. A human expert signs it. The customer gets a finished work product ahead of their deadline, with our name on the line.

Our customers hand us their most confidential material: unannounced acquisitions, pricing, landowner and counterparty details, deals that haven’t closed. Protecting it isn’t a compliance checkbox. It’s the reason they trust us with it at all. Every system you build treats customer data as strictly isolated, least-privilege and auditable from day one.

And we don’t get to be wrong. A hallucinated term in an IC memo isn’t a bug report, it’s a bad investment decision. Every claim we make must trace to a source page and span. When the evidence isn’t there, the system says so and routes the question to an expert. It never guesses. We’ll ship a “not found” before we ship a confident wrong answer.

We decide with facts, not vibes. Every meaningful change is an experiment: a hypothesis, a metric, a result. “It looks better” doesn’t ship. “Recall on termination rights is up 3 points with no false-positive regression” does.

The details are the job. Which document type regressed? Which clause produced the false positive? Does the gain hold on scanned amendments, or only on clean PDFs? In our world, a one-point bump in false-positive rate means real deals with wrong answers, so we notice it, explain it and fix it before it reaches a customer.

You’ll join our current two-person engineering team as the founding product engineer. You’ll work closely with our Founding AI/ML Engineer. You own the product: everything a customer, analyst or expert reviewer touches, and the platform it all runs on.

The model reads the documents. You make that work usable, checkable and trusted. Every term the agent extracts must link back to the page it came from. The expert who signs the memo needs to clear a deal in 40 minutes instead of 4 hours. A fund partner should be able to order diligence on Monday and have an IC memo they trust by Friday. These are product problems, and they’re yours.

The full loop is yours too: talk to the customer → define the product → sketch the UI → build it → ship it → watch it run on a live deal → optimize it.

• The analyst and reviewer workspace. Build the interface where experts check agent output: citations that open the exact clause, side-by-side document views, flags, redlines, sign-off. Every minute you save a reviewer is margin.
• The services workflow. Ordering, intake, deal status, deadlines, delivery. Build the system that lets us run many more deals with the same number of people.
• Applied AI. Build AI features end to end: prompts, tool use, structured outputs, agent workflows, and the UI around them. Make model output something customers can act on and trust. Work with the AI/ML engineer on evals and know when a feature needs deeper model work.
• Trust and privacy by design. Tenant isolation, permissions, audit trails and redaction for highly confidential deal data. Design every surface so customer data reaches only the people and models it should, and so that every answer shown to a user can be traced to its source.
• Human-in-the-loop by design. Decide where a person belongs in the loop and build the tools that make their judgment fast. Capture their corrections so they feed back into the AI system.
• Getting messy data in. Data rooms, email attachments, SharePoint dumps, 3,000-file zip archives. Build ingestion that copes with the real world.
• The platform. Infrastructure, deploys, telemetry and observability, and security and permissions for confidential deal data. You’ll ship to production on day one, on the system our customers’ deals run on.
• Deciding what we don’t build.

Rails, React, Postgres, AWS, and Hatchet for agent orchestration. We use Claude, OpenAI and Gemini, with an in-house eval harness. Our own coding agents are harness-agnostic and currently run on Claude Code.

• 4+ years building and shipping full-stack products used by real customers, ideally owning features from idea through production
• Strong product sense. You can sit with a customer, work out what they actually need, and sketch the answer before writing code
• Comfortable across the stack: frontend, backend, data model, infrastructure. You don’t wait for someone else to unblock you
• Hands-on applied AI experience. You’ve shipped LLM-powered features to real users, iterated on prompts and agent behavior, and dealt with what happens when the model is wrong
• You make decisions with data. You instrument what you ship, run experiments, and can tell a real effect from noise before acting on it
• Experience building software that handles sensitive data (financial, legal, health or similar), where access control and auditability are product requirements, not afterthoughts
• 0→1 ownership. You’ve been early somewhere, or built something from nothing, and you move fast without breaking the customer’s trust

• You’d rather ship three iterations in a month than polish one in a quarter
• You sweat the details others skip, and a small regression bothers you until you understand it
• You care about the experience of the person doing the work, not just the person buying the software
• You like workflow-heavy, high-stakes software where correctness and auditability matter
• You’re energized by ambiguity and know how to make progress anyway
• Bonus: you’ve worked in fintech, legal tech, energy, healthcare, or any domain where users stake their reputation on the output

• Meaningful equity at a seed stage company
• 401(k) with a match. Yes, a startup offering a match.
• Full health coverage for you and your family
• Remote (US)
• Whatever you need to get set up well at home
• All the AI tools and tokens you need

Email careers@buildq.ai with your resume and a short note about something you shipped that you’re proud of.