Overview

• Project: AI-powered real-time translation tool integrated with Zendesk to allow customer support agents to seamlessly communicate with customers in any language.
• This is a production-impact end-to-end project (not a lab exercise) as part of the company's digital transformation and AI roadmap.

Responsibilities / What you will do

• Design, develop, and test a custom translation system enabling automatic translation of incoming customer emails and chats into the agent’s language.
• Implement automatic translation of agent replies back to the customer’s language, glossary-based terminology control (product names, brand vocabulary), and Zendesk integration via a custom app or sidebar.

Technical environment

• Backend: Python / Node.js; Frontend: JavaScript / Zendesk App Framework (ZAF); Cloud: AWS.
• APIs & AI: Deepl, Open AI, or similar LLM services; Tools: Git, REST APIs, Webhooks.

Quality & Enhancement

• Translation quality enhancement using LLMs (post-editing, tone adaptation) and glossary-based terminology control.
• Integration considerations include real-time behavior in Zendesk, production robustness, and maintainability.

Candidate profile / Qualifications

• Final-year student in Software Engineering with strong foundations in software development, REST APIs, and web technologies (HTTP, JSON).
• Good programming level in Python, Node.js, JavaScript; interest in AI, Natural Language Processing, and LLMs; comfortable with Git and basic cloud concepts.
• Analytical mindset, strong problem-solving skills, good documentation and communication skills in English, and ability to work autonomously on a complex end-to-end technical project.

What We Offer (as stated)

• Duration: 6 months.
• Hands-on experience in developing a real-world application from scratch; opportunity to work with modern web technologies in a professional environment.
• Exposure to agile development methodologies and tools; flexible working hours and the possibility to work remotely.

How to apply

• Apply via BambooHR or the link shared in the post (see application_link).