Job description
Senior Generative AI Engineer
Virta Health is pioneering a new standard of care for people to reclaim their lives. We are in the midst of a public health crisis: obesity rates are at an all-time high and over half of US adults have type 2 diabetes or prediabetes, and despite billions spent on new treatments, outcomes are largely worse. Virta reverses these diseases and delivers life-changing results by pairing individualized nutrition with ongoing care from a clinical support team. We have raised over $350 million from top-tier investors, and partner with the largest health plans, employers, and government organizations to help their employees and members restore their health and take back their lives.
This role is a chance to help shape the future of Virta’s AI-powered coaching experience and contribute to reversing chronic conditions like diabetes and obesity at scale. As a key member of the technical leadership team, you’ll play a central role in evolving our GPT-based chatbot into a powerful platform that supports coaches, engages members, and drives real health outcomes. It’s a rare opportunity to work at the intersection of GenAI, behavioral health, and mission-driven impact. You’ll collaborate closely with product, design, and engineering partners to solve complex problems at the intersection of GenAI and behavior change. If you’re passionate about solving hard problems that actually help people, this is the role for you.
Responsibilities
Collaborate with cross-functional teams (product, design, engineering, and clinical experts) to evolve Viv, Virta’s GPT-powered chatbot, into a scalable platform.
Design and implement core infrastructure to support prompt orchestration, context management, experimentation, and evaluation at scale.
Contribute to the technical strategy for conversational AI—bringing a GenAI perspective to platform decisions, roadmap planning, and system architecture.
Write production-grade code and build robust ML systems that support continuous learning, monitoring, and iteration.
Mentor and guide teammates across disciplines, elevating engineering practices and GenAI fluency across the organization.
Measure and improve chatbot performance through data-driven iteration, focusing on member engagement, response quality, and outcome achievement.
90 Day Plan
Within your first 90 days at Virta, we expect you will do the following:
Month 1: Immerse & Align
You’ll hit the ground running by diving into Viv’s existing architecture, prompt frameworks, and conversational data. You’ll get familiar with our health coaching product, how Viv fits into the member journey, and the cross-functional team behind it—including product managers, engineers, designers, and coaching leads. You’ll also join strategic planning sessions to help shape where Viv goes next—and how your expertise can accelerate that vision.
By the end of Month 1, you’ll understand the key systems in place, the major opportunities ahead, and where your impact can be most immediate.
Month 2: Build & Experiment
You’ll start shipping. Expect to take the lead on experiments around prompt tone and engagement, testing different conversational styles and message formats to drive more member interaction. You’ll work on improving Viv’s context-awareness using event data and begin contributing to the platform architecture for message routing, experimentation, and testing.
By the end of Month 2, you’ll have launched your first experiments, contributed to platform infrastructure, and helped the team start to scale personalized, dynamic conversations.
Month 3: Extend & Lead
You’ll take on larger technical ownership—helping define the vision for proactive use cases, message prioritization, and coach-Viv collaboration systems. You’ll mentor other engineers, guide architecture decisions for upcoming features, and partner with product to prioritize high-impact roadmap items. You’ll also start to shape how Viv becomes a tool that every team at Virta can build on.
By the end of Month 3, you’ll be a go-to leader on the Viv team—pushing forward both technical innovation and cross-team alignment, and helping drive real engagement and health outcomes for our members.
Must-Haves
Experience with large language models (LLMs) such as OpenAI’s GPT, including prompt engineering and tuning for performance and engagement.
Strong software engineering skills, particularly in Python, with experience writing production-quality code.
Proven ability to design and build ML systems end-to-end, including experimentation frameworks, real-time pipelines, and monitoring infrastructure.
Experience deploying ML models in production environments, preferably on cloud platforms like Google Cloud Platform (GCP).
Background in building or contributing to internal platforms/tools that are used across multiple teams or products.
Familiarity with experimentation methods, including A/B testing and evaluation of conversational systems.
Comfort working cross-functionally—collaborating closely with product managers, designers, and engineering stakeholders.
Strong communication and technical leadership skills, including mentoring other engineers and aligning on technical decisions within a larger leadership team.
Track record of using data to inform iteration, particularly with user-facing ML products where engagement and outcomes are key success metrics.
Preferred Skills
Experience designing or optimizing conversational UX or working on chatbot platforms.
Familiarity with Retrieval-Augmented Generation (RAG) or similar methods for injecting user context into LLM prompts.
Prior work in health tech, digital coaching, or behavior change products.
Exposure to message routing systems or prioritization frameworks (e.g., trigger scoring, intent recognition, message sender selection).
Experience with LLM-specific integrations like OpenAI’s function calling, embeddings, or tool use patterns.
Knowledge of MLOps best practices, including CI/CD pipelines, container orchestration, and scalable model deployment.
Background in A/B testing for user engagement, particularly in GenAI or NLP-driven experiences.
Contributions to open-source GenAI tooling or external thought leadership (e.g., blog posts, talks, or research).
Understanding of ethical and responsible AI practices, especially in user-facing applications.
Values-driven culture
Virta’s company values drive our culture, so you’ll do well if:
You put people first and take care of yourself, your peers, and our patients equally
You have a strong sense of ownership and take initiative while empowering others to do the same
You prioritize positive impact over busy work
You have no ego and understand that everyone has something to bring to the table regardless of experience
You appreciate transparency and promote trust and empowerment through open access of information
You are evidence-based and prioritize data and science over seniority or dogma
You take risks and rapidly iterate
Is this role not quite what you’re looking for? Join our Talent Community and follow us on Linkedin to stay connected!
As part of your duties at Virta, you may come in contact with sensitive patient information that is governed by HIPAA. Throughout your career at Virta, you will be expected to follow Virta’s security and privacy procedures to ensure our patients’ information remains strictly confidential. Security and privacy training will be provided.
#LI-remote
Virta has a location based compensation structure. Starting pay will be based on a number of factors and commensurate with qualifications & experience. For this role, the compensation range is $220,439 - $276,101. Information about Virta’s benefits is on our Careers page at: https://www.virtahealth.com/careers .
As part of your duties at Virta, you may come in contact with sensitive patient information that is governed by HIPAA. Throughout your career at Virta, you will be expected to follow Virta’s security and privacy procedures to ensure our patients’ information remains strictly confidential. Security and privacy training will be provided.
As a remote-first company, our team is spread across various locations with office hubs in Denver and San Francisco. We currently do not hire in the following states: AK, AR, DE, HI, ME, MS, NM, OK, SD, VT, WI.
#LI-remote
