Senior Software Engineer (Backend)

ABOUT OUR COMPANY

At Hyperscience, we believe that behind every document is a meaningful human experience, whether that’s a family applying for their mortgage, a patient waiting for insurance coverage, or a student waiting for their visa to study abroad. However, for far too long, organizations have relied on outdated technology and manual processes to handle these processes, driving up costs, slowing down decisions, and frustrating customers.

As a distinguished leader in its market category, including a back to back Leader in the 2025 & 2026 Gartner Magic Quadrant for Intelligent Document Processing Solutions and several other leading industry analyst reports https://www.hyperscience.ai/why-were-a-leader/#:~:text=Hyperscience%20has%20been%20named%20to,top%20spot%20on%20the%20list., our technology flips the script with an AI platform that reads, understands, and processes documents at massive scale—automatically.

The Hyperscience Hypercell platform unlocks the value of an organization’s back office data through the automation of end-to-end processes, and transforms complex documents into LLM and RAG-ready data to power new enterprise GenAI experiences. This enables organizations to transform manual, siloed processes into a strategic advantage, resulting in a faster path to decisions, actions, and revenue; positive and engaging customer, public, and patient experiences; and dramatic increases in productivity.

Leading organizations including American Express, Charles Schwab, HM Revenue and Customs, Mars, Stryker, The United States Social Security Administration, The United States Department of Veterans Affairs, and several others use the Hypercell platform to achieve a faster path to decisions, dramatic increases in productivity, and unparalleled business impact.

Hyperscience is funded by top tier investors including Bessemer Venture Partners, Battery, FirstMark, Stripes, and Tiger Global.

ABOUT THE ROLE:

Hyperscience converts documents (such as insurance claims, loan applications, and benefit forms) into structured, actionable data for major enterprise systems. Our backend is a Python/Django system that ingests documents, uses ML models and LLMs for classification and extraction, routes low-confidence results to human reviewers, and exports structured data to downstream systems. Customers run Hyperscience in their own environments and build custom workflows via our Flows SDK.

In this role, you will contribute across the core application and assist with customer workflow integrations.

KEY RESPONSIBILITIES:

- Document processing: Design and maintain end-to-end processing features (ingestion, layout detection, classification, field extraction, normalization, and validation), focusing on backend orchestration and fallback logic around ML/LLM models.

- Human review pipeline: Develop task routing, review logic, and APIs powering the human review UI, ensuring corrections feedback directly into model retraining datasets.

- Training data & model lifecycle: Build services to store, import/export, version, and sanitize (PII deletion) training data to support custom model retraining.

- APIs & integrations: Evolve versioned REST APIs (OpenAPI) and expand connectors for platforms like Salesforce and MuleSoft, alongside configuration migration tooling.

- Workflows & background tasks: Optimize the workflow engine and task queue for high concurrency, minimal database round-trips, and clear error handling.

- Customer workflows: Implement and review production customer workflows using the Flows SDK, channeling feedback to improve core platform APIs.

- Engineering standards & AI tooling: Leverage AI development tools (Claude Code, Copilot) and maintain repository agent rules and automated code review guidelines.

- Mentorship & collaboration: Perform cross-team code reviews, document system architecture, and assist peers with database query optimization and schema migrations.

REQUIRED QUALIFICATIONS:

- 5+ years