AI Engineer - Conversational Agents (LLM)

About UsAt Diagnostic Robotics, we’re building AI-driven voice and chat agents to empower healthcare providers, payers, and value-based care teams. Our technology predicts adverse health events, enables early intervention, and automates routine administrative tasks, ultimately reducing costs, easing provider burden, and improving patient outcomes.Our conversational agents leverage state-of-the-art LLMs to interact naturally with patients and care teams, delivering real value at scale.The RoleWe’re seeking a hands-on AI Engineer with both research expertise and engineering experience to lead the development of the AI core of our conversational agents. You will own the end-to-end AI lifecycle from design and KPI definition, through model development, fine-tuning, and evaluation, to deployment and continuous optimization in production.You’ll work in a fast-moving startup environment, collaborating closely with our engineering team to integrate advanced AI capabilities directly into our product.Key ResponsibilitiesResearch & Innovation:- Stay up to date with the latest in LLMs, generative AI, and multi-agent systems.- Experiment with new methods and evaluate their real-world performance.Prompt Engineering:- Design, test, and optimize prompts to achieve desired conversational behaviors and outputs.- Develop prompt libraries, templates, and automated testing frameworks for reliability and consistency.-Model Development & Optimization:- Adapt LLMs for specific use cases.- Optimize for speed, accuracy, and cost.Performance Measurement:- Define KPIs for conversational agent quality and effectiveness.- Build evaluation frameworks to continuously monitor and improve agent performance in production.Engineering & Deployment:- Design, implement, and maintain production-ready AI pipelines in Python (and optionally Node).- Handle large-scale data ingestion, preprocessing, and analysis.- Integrate AI modules into the overall product architecture in collaboration with the core engineering team.RequirementsMust-HaveMaster’s or PhD in Computer Science, AI/ML, Mathematics, or a related field.4+ years of professional development experience in Python (Node.js is a plus).Proven applied research experience in LLMs, NLP, or conversational AI.Strong track record of deploying AI models to production and iteratively improving them with real-world feedback.Expertise in prompt engineering and multi-agent systems.Solid understanding of performance metrics and evaluation methodologies for AI agents.Strong communication skills and ability to work effectively in a small, collaborative team.Nice-to-HaveExperience in cloud environments (AWS, GCP, Azure).Background in healthcare technology and compliance (HIPAA, HL7/FHIR).BenefitsImpact: Your work will directly influence patient care and healthcare efficiency.Ownership: You’ll be the AI lead in a small, fast-moving team—your decisions will shape the product.Innovation: Work at the cutting edge of LLM-based conversational AI in a real-world, high-impact domain.