Build document ingestion workflows for PDFs, DOCX, and image files.
Work with AI models, prompts, schemas, structured outputs, and OCR.
Build asynchronous processing using S3, SQS, DynamoDB, and worker services.
Create automated tests and extraction-quality evaluations.
Troubleshoot production issues using logs, metrics, traces, and New Relic.
Contribute to Docker, Terraform, Helm, and Amazon EKS deployments.
Demonstrate autonomy and operate with minimal supervision.
- Follow best security practices for authentication, API scopes, tenant isolation, and data documentation.
- Minimum Qualifications:
- 4+ years of experience building complex products.
Proficiency in the Python programming language.
Experience with REST APIs, background processing, databases, cloud services, and automated testing.
Understanding of AI applications, prompt design, structured outputs, tool calling, and response validation.
Experience with monitoring and troubleshooting production systems.
Experience using Codex/Cursor AI coding tools.
Strong problem-solving and communication skills.
Ability to communicate effectively with teams across Entrata.
Experience with LLM APIs integrations
Experience with FastAPI, Pydantic, pytest, PyMuPDF, or AWS Textract.
- Knowledge of AWS services like S3, DynamoDB, and SQS
- Preferred Qualifications:
- Knowledge of Deployment services like Docker, Terraform, Helm, or Amazon EKS.
Experience with document-vision models and document extraction evals.
Familiarity with JWT, API scopes, New Relic, Langfuse, Vue, or Tailwind CSS.