This is a fully remote position, open to applicants in United States, +16 more locations.

📋 Description

• Establish the technical standards for chatbot systems and influence the future initiatives of the prompt engineering team.

• Ensure a robust chatbot architecture as it expands.

• Create automations for handling record disputes, reducing email/callouts, and validating documents.

• Assess new AI technologies such as voicebots and computer-use agents.

• Determine which technologies should be prioritized for future investment.

• Develop and deploy AI systems into production.

• Collaborate with OpenAI to assess and implement next-generation voice models and workflow automation.

• Design the next-generation AI system for insurance quoting, document validation, stateful phone interactions, and seamless navigation of external insurance systems.

⛳️ Requirements

• Over 5 years of experience in software engineering.

• Ideally, experience at an early-stage startup with complete ownership of projects.

• In-depth practical experience with AI and the capability to work with newly released models.

• Proficient in articulating the advantages of one AI architecture or approach over another.

• Experience in deploying LLM-based systems into production environments.

• Familiarity with evaluations, regressions, latency, costs, and error handling.

• Proficiency in TypeScript, including Nest.js and React.

• Experience with GraphQL.

• Knowledge of AWS services, including ECS/EKS and Lambda.

• Familiarity with LLM models such as OpenAI, Anthropic Claude, and Google Gemini.

• Must currently reside in an eligible hiring location: Arizona, California, Colorado, Florida, Georgia, Illinois, Massachusetts, North Carolina, New Jersey, Nevada, New York, Oregon, Tennessee, Texas, Utah, Virginia, or Ontario, Canada.

• Legal authorization to work in the U.S. or Canada is required.

• Must be able to work full-time as a salaried employee.