Build, deploy, and maintain intelligent agents, chatbots, and generative AI systems using large language models (LLMs) and retrieval-augmented generation (RAG) frameworks.
Develop end-to-end AI applications from backend APIs and data pipelines to front-end interfaces, integrating machine learning, NLP, and user experience best practices.
Create, test, and refine high-performing prompts, chains, and system instructions to optimize LLM responses and reliability across use cases.
Implement, fine-tune, and evaluate large-scale foundation models for domain-specific tasks.
Develop and maintain AI development environments, orchestration frameworks, and CI/CD pipelines for model deployment and scaling in cloud or hybrid environments.
Measure and optimize model accuracy, latency, cost efficiency, safety, and fairness using quantitative metrics and human evaluation loops.
Ensure AI solutions meet enterprise-grade security, privacy, and governance standards, including model observability and traceability.
Collaborate with product managers, designers, and data scientists to translate business needs into scalable AI-powered features and solutions.
Research and implement emerging tools, frameworks, and techniques in LLM optimization, model evaluation, and AI infrastructure to enhance system performance.
Maintain thorough technical documentation, model cards, and operational playbooks; mentor peers in AI best practices.
Designs automated and human-in-the-loop evaluation frameworks to ensure the quality, factual soundness, and empathy of AI-generated responses in real call environments.
Monitors conversational telemetry including latency, model confidence, and escalation rates to identify opportunities for prompt and logic refinement.
Implements AI judge models and scoring pipelines that measure relevance, accuracy, and tone alignment with Humana's service standards and compliance requirements.
Build and manage AI-ready data infrastructure to support machine learning, LLMs, and advanced analytics.
Design and maintain feature stores and data pipelines for model training and real-time inference.
Implement and manage vector databases, embedding pipelines, and retrieval-augmented generation (RAG) frameworks for generative-AI applications.
Fine-tune foundation models and develop retrieval-augmented generation (RAG) pipelines.
