Responsibilities :

• Design, write, and maintain automated test suites for backend services and data-extraction pipelines.
• Build and run tests that validate OCR and LLM output accuracy against expected results.
• Identify, document, and track bugs, working closely with engineers to resolve them.
• Develop test data sets and scenarios that cover a range of document types and edge cases.
• Contribute to integration and regression testing as part of the CI/CD pipeline.
• Monitor test results and pipeline health for deployments running on Azure.
• Collaborate with software engineers and product to understand requirements and acceptance criteria.
• Continuously improve test coverage and automation practices as the platform evolves.

Qualifications :

• A degree in Computer Science, Software Engineering, or a related field (recent graduates encouraged to apply).
• Basic understanding of Python (scripting, data structures, working with libraries).
• Understanding of core QA concepts (test cases, test plans, bug lifecycle, regression vs. smoke testing).
• Familiarity with version control (Git).
• Basic understanding of REST APIs and how backend services communicate.
• Comfortable working with structured data formats such as JSON.
• Strong attention to detail and analytical thinking.
• Good communication skills and ability to work in a team environment.
• Curiosity about AI/LLMs, OCR technologies, and how to test them effectively (no prior professional experience required – we’ll teach you).

Preferred Qualifications :

• Academic or personal projects involving test automation (e.g., pytest, Selenium, Playwright).
• Exposure to API testing tools (e.g., Postman, requests library).
• Familiarity with cloud concepts (especially Azure) or containerization (Docker).
• Basic understanding of CI/CD concepts and tools (e.g., GitHub Actions, Azure DevOps).
• Exposure to OCR or LLM-based systems through coursework, hackathons, or personal projects.

משרה מלאה במתחם HUBayta בגליל

‍

‍

Responsibilities :

• Develop and maintain backend services in Python that support document ingestion, OCR processing, and LLM-based extraction workflows.
• Write clean, well-tested code and participate in code reviews.
• Help debug and improve existing extraction pipelines (accuracy, performance, reliability).
• Work with APIs (internal and third-party, including LLM providers) to integrate new capabilities.
• Contribute to writing unit/integration tests and basic CI/CD practices.
• Collaborate with senior engineers, product, and QA to understand requirements and ship features.
• Deploy, monitor, and support backend services running on Azure.

Qualifications :

• A degree in Computer Science, Software Engineering, or a related field (recent graduates encouraged to apply).
• Solid understanding of Python fundamentals (data structures, OOP, basic algorithms).
• Familiarity with version control (Git).
• Basic understanding of REST APIs and how backend services communicate.
• Comfortable working with data formats such as JSON, and reading/writing structured data.
• Strong problem-solving skills and eagerness to learn new technologies.
• Good communication skills and ability to work in a team environment.
• Curiosity about AI/LLMs and OCR technologies (no prior professional experience required – we’ll teach you).

Preferred Qualifications :

• Academic or personal projects involving Python backend development.
• Exposure to OCR libraries (e.g., Tesseract, EasyOCR) or document-processing tools.
• Exposure to LLM APIs (OpenAI, Anthropic, etc.) through coursework, hackathons, or personal projects.
• Familiarity with Docker, cloud concepts (especially Azure), or SQL/NoSQL databases.
• Experience with testing frameworks (pytest, unittest).

‍

משרה מלאה במתחם HUBayta בגליל

‍