You will be part of a delivery team for a contract intelligence engagement. The system reads large sets of

related legal documents (master agreements, amendments, addenda, exhibits, schedules) and answers questions

about what those documents say and which terms are in force at a given date.

You should have strong full stack engineering skills plus practical LLM application experience.

Prior experience on a legal or contract heavy project is a must have. Deeper legal or contracts knowledge beyond

that baseline is a differentiator for this role.

• Building and shipping the application end to end: backend services in Python and a modern web frontend.

• Building document viewing and review experiences: side by side clause comparison, citation highlighting on

the original page, version history across amendments, and reviewer feedback capture.

• Integrating with the AI layer: agent loops, tool use, agent skills, and MCP servers.

• Handling large document sets, long running jobs, and streaming responses without degrading the interface.

• Owning quality: testing, observability, performance, and access control over sensitive documents.

Representative Questions the System Must Answer

These are provided so applicants understand what the interface they will build has to expose and defend. Applicants do not need

to answer them, but must understand why each one is hard to present to a user:

• The master agreement caps liability at 12 months of fees, with carve-outs for confidentiality and IP indemnity.

A data breach occurs under a security exhibit added by a later amendment. Is the exposure capped?

• Amendment 2 restated a section in full. Amendment 4 modified one sentence of that section. What is in force

today, and what is the citation?

• The SOW sets a 30 day notice period and the master agreement sets 90 days. The master agreement has no

order of precedence clause. Which governs?

• Does this agreement contain a most favored nation clause? If it does not, how was that established?

• Which obligations survive termination, and for how long?

Every one of these produces an answer that a user will want to verify against the source before acting on it. The

interface has to make that verification fast.

Technical Requirements

• Strong Python on the backend and strong modern frontend (TypeScript with React or equivalent).

• Practical experience integrating LLM applications built on a production agent SDK, including agent loops,

tool use, agent skills, and MCP.

• Comfortable working with documents at scale: PDF rendering, OCR output, image parsing, and table data.

• Cloud infrastructure, CI/CD, and production operations.

• Senior level autonomy: able to take a vague requirement to a shipped feature without supervision.

Legal and Contracts Experience

Must have: prior work on a legal, contract, or document heavy product or project. This is what gives you

the intuition for what a legal or commercial user actually needs from the interface.

Differentiator, beyond the must have: deeper legal or contracts knowledge, including:

• Familiarity with how master agreements, amendments, addenda, and exhibits fit together, and why "which

version is in force" is a real question.

• Experience building tools used by legal, contract management, or compliance teams.

• An intuition for why a citation to the exact clause and page matters more here than a well written summary.