ABOUT THE ROLE

We're looking for a Senior Full Stack Developer to build and maintain production systems for our Document Intelligence platform.

Our extraction engine leverages a wide set of tools such as OCR, LLMs, and purpose-built ML models to extract data from complex documents at scale: legal documents, poor-quality scans, embedded diagrams, tabular images, and dense technical documents to name a few. In addition to automation of data extraction at scale, we emphasize quality with a specialized human-in-the-loop interface, ensuring accuracy of extractions before delivering data downstream. You'll work across our extraction pipeline, web application, and integration layers to produce high quality code and build features at enterprise scale.

The ability to leverage AI tools for rapid development while maintaining a high degree of code quality is crucial to this role. We need someone who can reason through pull requests and talk about why code works, offer technical trade-offs, and suggest improvements. You'll use your technical acumen to judge the output of an LLM to be production-worthy or a confident hallucination. You can discern when something doesn't look right, and collaborate with the team when necessary to ensure high quality as we scale. You don't hand off to QA until you'd sign your name to it.

Our ideal candidate could also contribute as a Forward-Deployed Engineer on our Solutions Delivery Team - a small, tactical group that works directly with customers to deploy and integrate our platform within their environments and third-party systems. This work requires comfort across APIs, databases, and external integration points, with particular attention to security, permissions, reliability, and scalability. You would participate in customer conversations to understand requirements, shape practical solutions, and troubleshoot issues through deployment. We value pragmatic engineers who communicate clearly, collaborate generously, and make sound technical decisions under real-world constraints.

Responsibilities

• Design, build, and maintain full-stack features across our Document Intelligence platform (React/TypeScript front-end, Node/Python back-end, PostgreSQL and Graph databases).
• Build and maintain extraction pipeline components that orchestrate multiple AI models and tools (LLMs, VLMs, OCR) with deterministic validation layers and automated testing.
• Build and maintain integrations with Microsoft ecosystem services (E.g. SharePoint, Azure AI, Copilot Studio, Power Platform, MCP).
• Debug complex issues across distributed systems, such as pipeline failures and optimization tuning.
• Contribute to internal tooling, automation, and developer experience improvements.
• Stay current with industry trends and recommend new tools or approaches where they genuinely improve the product or process.

Requirements

• 5+ years of professional software development experience, with demonstrated full-stack depth.
• Strong proficiency in TypeScript, React, Node.js, and PostgreSQL. Python experience valued.
• Production experience building systems that integrate LLMs/AI models: using APIs, managing prompts, handling nondeterministic outputs, implementing validation, and controlling cost.
• Solid understanding of software architecture fundamentals: design patterns, separation of concerns, and the ability to assess whether a proposed approach will hold up as the system grows.
• Strong Git workflows, CI/CD practices, and automated testing discipline.
• Conduct rigorous reviews of code: evaluate for correctness, security, maintainability, and fit within the existing system. You can spot hallucinated patterns, security gaps, and architectural misalignments. You make pragmatic decisions on when to fix it yourself versus when to flag it for the team.
• Clear, direct communication. Ability to raise concerns, ask good questions, and collaborate without ego.

Preferred Qualifications

• Familiarity with multi-modal AI systems and automation workflows.
• Experience with SharePoint APIs and Microsoft 365 integration patterns.
• Familiarity with containerization (Docker, Kubernetes) and infrastructure-as-code.
• Experience in document processing, metadata extraction, or enterprise content management domains.
• Experience with automated testing tools and frameworks such as Playwright.
• Knowledge of MCP (Model Context Protocol), RAG (Retrieval Augmented Generation) and similar agent communication standards.

Solutions Delivery Experience (Valued)

• Third-party integrations. Experience building and maintaining integrations with external systems. Working through multiple APIs, varied authentication models, and real-world data quality issues to deliver reliable solutions.
• API and database fluency. Strong hands-on experience designing, building, and troubleshooting RESTful APIs and working with relational databases in production environments.
• Customer-facing communication. Comfortable joining calls with customers or partners to scope technical requirements, explain trade-offs in plain language, and collaborate on solutions without needing a translator between engineering and business.
• A team player who makes practical decisions under real constraints: balancing quality, timeline, and scope without over-engineering or cutting corners. You solve the problem in front of you and move on.