AI Application Engineer

Position Summary

Lirio is healthcare’s leading personalization engine that empowers healthcare organizations to better engage consumers on their journey to better health. Lirio leverages an approach called Precision Nudging™ – combining behavioral science and AI to drive meaningful health outcomes by assisting each person in their unique healthcare experience. By scaling personalized interventions, our clients deliver consumer-focused experiences that initiate and drive sustained behaviors across their entire population, optimizing consumer engagement, closing gaps in care, lowering costs, and measurably improving health outcomes. The AI Application Engineer will work closely with the rest of the AI team, and interface with the broader technical organization, to fine-tune, optimize, deploy, and maintain generative AI models within the broader product offering. This role requires combined expertise in software development, programming, data engineering, and generative AI technologies.

Essential Duties & Responsibilities

• Training, fine-tuning, alignment and other engineering tasks required for the customization and deployment of new conversational AI models backed by specialized LLMs.
• Enhancing capabilities of conversational agents (e.g., through interoperability with other tools and agentic models).
• Design, implementation, testing, deployment, and maintenance of production software in compliance with Lirio’s practices and methodologies in software engineering, including an emphasis on quality and security.
• Collaborate with cross functional teams to define project requirements and deliver scalable solutions.
• Conduct testing and optimization of AI models, ensuring high performance and accuracy.
• Participation in planning/agile ceremonies.
• Stay up to date on the latest Generative AI technologies/advances.
• The ideal candidate will have extensive experience in RLHF, DPO, RAG, CoT reasoning, MCP and other agentic communication protocols, etc.

Qualifications

• Master's degree preferred
• 3-5 years of relevant experience
• Extensive experience in the development and deployment of LLM-based technologies in production environments.
• Knowledge of MCP and other agentic communication protocols
• Knowledge of cloud platforms (AWS, Google Cloud, Azure) and deployment strategies
• Proficiency in programming languages Python, Java, C++
• Extensive knowledge of or direct experience with a variety of tools and open-source libraries related to LLM customization and deployment (e.g., fine-tuning and optimization libraries, evaluation frameworks, inference and serving engines, etc.)
• Additional areas of experience/expertise that are preferred for this role include mobile application development, voice-related technologies, multi-lingual language models, and application of LLMs in the healthcare sector, including familiarity with the relevant regulatory requirements.

Benefits

• Medical (HSA available)
• Dental
• Vision
• Short-term & long-term disability (company-paid)
• Life & AD&D (company-paid)
• 401K with company match
• 10 paid holidays + holiday week company closure
• Flexible time off policy
• Work from home
• Salary Range: $120,000-$150,000