Take part in designing and building AI components used in customer-facing GenAI agents across both chat and voice platforms.
Help develop complex inference pipelines that combine multiple models — such as those used for embedding-based search or speech-to-text and natural language understanding.
Build integrations that connect AI agents with various internal APIs via MCP, enabling them to perform dynamic actions and generate contextual responses.
Maintain and improve retrieval-augmented generation (RAG) systems and support the testing and iteration of prompts to enhance response quality.
Work closely with senior engineers and DevOps teams to deploy AI models and services in scalable environments based on Kubernetes and Microsoft Azure.
Support monitoring, logging, and evaluation processes, including experiment tracking and feedback loop implementation.
Handle anonymized or sensitive user data responsibly, ensuring full compliance with GDPR and internal data governance policies.
Participate in documentation efforts, team discussions, and knowledge-sharing sessions to support collaboration and continuous learning.
requirements-expected :
A degree in Computer Science, Data Science, Artificial Intelligence, or a related discipline — or equivalent professional experience.
Several years of hands-on experience developing AI and Machine Learning solutions, preferably in the context of Customer Support or Customer Experience.
Strong skills in Python and familiarity with leading NLP libraries and tools.
Practical experience working with Microsoft Azures AI ecosystem, such as Azure Machine Learning, Cognitive Services, and Bot Framework.
Solid grasp of cloud-native architectures and microservices, particularly within the Azure environment.
Experience designing and working with CI/CD workflows and applying MLOps practices to manage the ML lifecycle.
A strong analytical approach and the ability to effectively solve complex technical challenges.
