remote
Senior AI Agent & Evaluations Engineer - Vacatia, Inc.
Software Engineer
Senior AI Agent & Evaluations Engineer building AI agents that automate complex vacation‑ownership workflows using Python, ML, and NLP, while designing rigorous evaluation frameworks to ensure performance and reliability.
About the role
Key Responsibilities
- Design, develop, and deploy AI agents that automate decision‑making and customer support across vacation‑ownership workflows.
- Build and maintain evaluation pipelines to benchmark agent performance, including precision, recall, and user‑experience metrics.
- Collaborate with data scientists and product teams to refine models, incorporate feedback loops, and iterate on agent capabilities.
- Implement robust data pipelines and feature engineering for large, heterogeneous datasets.
- Document architecture, best practices, and evaluation results for internal stakeholders.
Requirements
- 5+ years of experience in AI/ML engineering with a focus on agent or chatbot development.
- Proficiency in Python, TensorFlow/PyTorch, and NLP libraries (spaCy, Hugging Face).
- Strong background in evaluation methodology, A/B testing, and statistical analysis.
- Experience with cloud platforms (AWS, GCP) and CI/CD for ML workflows.
- Excellent communication skills and ability to translate technical findings into actionable insights.
Skills
pythonmachine learningnlp