Software Engineer, Applied AI

Hi, we’re Gravie. Our mission is to create health benefits that actually benefit small and midsize businesses and their employees. Our innovative benefit solutions and services are developed and delivered by a diverse group of unique people. We encourage you to be your authentic self - we like you that way.

At Gravie, engineers work closely with Product and own outcomes end to end. That means understanding the business deeply, shaping the problem and solution, and staying accountable for whether what we build actually solves the problem—not simply implementing a set of requirements.

We practice agentic development to increase the scope and leverage of that ownership. Engineers start with a clear outcome or problem, use AI agents to help develop the specification and proposed plan, and then use those agents to execute substantial multi-step engineering work. Engineers review and refine the spec and plan, set guardrails and acceptance criteria, validate the results, and own the quality of everything that ships.

As agents take on more of the execution, the bar for engineers gets higher. Strong problem framing, business understanding, architectural judgment, system thinking, risk identification, and the ability to evaluate quality, maintainability, and tradeoffs become even more important.

• Design and build production-grade AI agent systems, including multi-agent workflows, orchestration layers, and the infrastructure needed to make them reliable, observable, and auditable.

• Design retrieval, context, and memory architectures that ground AI outputs and support reliable multi-step workflows.

• Lead the development of AI-powered decision-support systems that meet the accuracy, traceability, and explainability requirements of healthcare and other regulated environments.

• Architect distributed services, event-driven workers, job pipelines, state management, failure recovery, APIs, and data models.

• Guide the development of intuitive, product-quality experiences using React and Type Script that make complex AI capabilities understandable and actionable.

• Establish organization-wide patterns for AI quality and safety, including automated evaluations, regression testing, groundedness checks, compliance guardrails, and production monitoring.

• Define standards for deploying and operating AI-enabled systems through CI/CD, cloud infrastructure, observability, alerting, and production support.

• Mentor senior engineers, lead architecture reviews, resolve cross-team risks, and shape technical roadmaps.

• Serve as a trusted technical advisor to Engineering, Product, Data, Security, Infrastructure, and business stakeholders.

• Set technical direction for Gravie's AI-enabled products, platforms, retrieval systems, model integrations, and shared capabilities.

• Ten or more years of software engineering experience, including technical leadership of complex, distributed systems from design through production.

• Demonstrated experience setting technical direction across multiple teams or product areas.

• Hands-on experience building and operating production AI applications, not only prototypes.

• Hands-on experience with agentic software development, using AI coding agents to help create specifications and plans, execute meaningful multi-step work across a codebase, run and fix tests, validate results, and iterate while maintaining ownership of architecture, quality, and what ultimately ships.

• Deep expertise in at least one primary area, such as Python backend and distributed systems, or React and Type Script product engineering, with sound judgment across the full system.

• Experience with retrieval, embeddings, context, memory, evaluation, monitoring, or AI agent architectures and workflows.

• Experience establishing engineering standards for cloud infrastructure, CI/CD, observability, reliability, and production operations.

• Demonstrated experience designing evaluation, testing, monitoring, and continual-improvement practices for AI systems.

• Strong understanding of security, privacy, access control, data governance, auditability, and compliance considerations for AI systems.

• Proven ability to lead through influence, align…