What are the responsibilities and job description for the AI Engineer position at Apexon?
We are seeking a Conversational AI Engineer to design, implement, and enhance a Generative AI-powered virtual assistant leveraging advancements in Natural Language Processing and Large Language Models.
Conversational AI Engineer
Location: Lansing, MI (Hybrid – Onsite Mondays and Tuesdays)
Key Responsibilities
- Develop and optimize a Generative AI-powered virtual assistant for dynamic and context-aware responses
- Leverage large language models, prompt engineering, and fine-tuning techniques within Vertex AI
- Implement and refine conversational experiences in Dialogflow CX, incorporating Playbooks and Tools
- Analyze chatbot performance using BigQuery and Looker Studio to identify areas for improvement
- Enhance AI reasoning and retrieval-augmented generation techniques to improve knowledge retrieval
- Integrate Google Cloud Functions for seamless backend automation
- Ensure AI solutions align with business goals and compliance requirements
- Monitor and iterate on AI model performance, implementing continual improvements
Required Qualifications
- Experience developing AI-powered chatbots using Dialogflow CX and Vertex AI
- Strong understanding of Generative AI, large language models, natural language processing, and prompt engineering
- Proficiency in Google Cloud Services, including Vertex AI, BigQuery, Looker Studio, and Cloud Functions
- Experience analyzing AI performance metrics to enhance chatbot accuracy
- Ability to translate business needs into effective AI-driven solutions
Preferred Qualifications
- Proficiency in Python or JavaScript for AI model integration
- Experience with retrieval-augmented generation-based AI approaches for knowledge retrieval
- Experience deploying infrastructure as code using Terraform
- Familiarity with APIs, cloud security best practices, and AI ethics
