Description

You will build and maintain AI agents and chatbots, integrating machine learning models with production-grade software systems.

This role is on-site.

Responsibilities

• Develop and deploy AI agents using Python, Java, JavaScript, or C# with a focus on robust engineering practices.
• Implement Retrieval-Augmented Generation (RAG) pipelines, managing embedding models, vector databases, and unstructured data.
• Design and optimize prompt engineering strategies, including few-shot examples and structured output formatting.
• Build and consume RESTful APIs and microservices to integrate AI capabilities into existing software architectures.
• Debug complex issues by distinguishing between model behavior anomalies and code-level defects.

Required Skills

• 5+ years of professional software engineering experience.
• Strong proficiency in Python; familiarity with Java, JavaScript, or C#.
• Solid understanding of machine learning and AI concepts, including NLP and chatbot frameworks.
• Experience with Git version control, unit testing, and data structures (lists, dictionaries, trees, graphs).
• Proficiency in handling JSON and XML data formats.
• Ability to construct and iterate on prompts for reliable model outputs.
• Knowledge of vector databases and embedding techniques for data retrieval.

Preferred Skills

• Experience with Agile methodologies and sprint-based delivery.
• Understanding of ethical AI considerations, including bias detection and data confidentiality.

Key Skills

Education

Bachelor's degree