About the Role

We are expanding the team behind a production-grade platform that ingests purchase agreements and related contracts, processes them through OCR and large language models, and extracts contractual obligations, counterparties, and key terms with full clause-level traceability.

This is a hands-on, end-to-end engineering role for a senior generalist who enjoys owning features across backend services, AI integrations, frontend development, infrastructure, and deployment. You will work as part of a small engineering team where autonomy, ownership, and broad technical capabilities are highly valued.

What You'll Do

Extend the document extraction pipeline to support new agreement types and contract fact extraction.

Improve recall and accuracy for long, multi-party contract processing.

Build verification and grounding mechanisms to determine when model outputs can be trusted, escalated, or rejected.

Develop classical machine learning capabilities for document classification, routing, confidence scoring, and entity matching.

Enhance the review interface used by legal professionals and asset management teams.

Design and evolve relational data models supporting document versioning and supersession.

Implement and maintain cloud infrastructure, deployment pipelines, and operational tooling on GCP.

Collaborate directly with business stakeholders to translate contractual and operational requirements into product functionality.

Required Qualifications

5–8 years of professional software engineering experience.

Strong Python development experience using modern Python (3.9+), type annotations, and backend frameworks such as Flask, FastAPI, or Django.

Experience with SQLAlchemy 2.0 and PostgreSQL data modeling.

Production experience building LLM-powered document extraction solutions using structured outputs and JSON Schema.

Experience with platforms such as Vertex AI, Bedrock,



Azure OpenAI, Gemini, Claude, or equivalent.

Strong understanding of non-deterministic AI system evaluation, including regression testing, recall measurement, snapshot testing, and run-to-run comparisons.

Experience applying classical machine learning techniques to text classification problems using scikit-learn or equivalent tools.

Hands-on experience with OCR and document-processing platforms such as Google Document AI and pypdf.

Strong Google Cloud Platform experience including Cloud Run, Cloud SQL, Cloud Storage, Secret Manager, Identity-Aware Proxy, and Vertex AI.

Experience with Terraform, Docker, GitLab CI/CD, and security scanning practices.

Frontend development experience using Jinja2, Tailwind CSS, semantic HTML, accessibility standards, and vanilla JavaScript.

Strong automated testing discipline using pytest and JavaScript testing tools.

Preferred Qualifications

Microsoft Graph API and SharePoint integration experience.

Legal-tech, contract-management, or compliance domain expertise.

Renewable energy or power markets experience.

Experience partnering directly with non-technical stakeholders.

Technical Environment

Python 3.9+

Flask

SQLAlchemy 2.0

PostgreSQL

Gemini

Claude

Google Document AI

Vertex AI

Docker

Terraform

GitLab CI/CD

Tailwind CSS v4

Jinja2

Vanilla JavaScript pytest

Cloud Run

Cloud SQL

Cloud Storage

Core Competencies

End-to-end ownership

Problem solving

Product mindset

AI systems evaluation

Attention to detail

Collaboration

Communication

Technical versatility

Why Join Us

Work on a real-world AI platform solving complex document intelligence challenges.

Build systems where accuracy, explainability, and traceability matter.

Influence architecture, product direction, and engineering standards.

Own impactful features from design through production deployment.

Collaborate within a highly autonomous and technically strong team.

📌 Senior AI / Full-Stack Engineer – Document Intelligence (Colombia)
🏢 Automation USQ
📍 Colombia