Senior AI Development Platform Engineer

Lirio is a technology/software company that provides expertise in a variety of behavioral science domains (e.g., behavioral economics, social psychology, public health), data science, and machine learning to drive consumer engagement, close gaps in preventive and chronic care, and promote health and well-being across an individual's lifespan. Lirio's behavior change AI platform unites behavioral science with advanced artificial intelligence (AI) to deliver Precision Nudging health interventions. Precision Nudging is the application of behavioral science to health interventions personalized by AI to each individual that overcome barriers to action at the right time and place for scalable, behavior change. This is a remote role with the opportunity to be hybrid if located in Tennessee. All applicants must be authorized to work in the US without sponsorship. To ensure an excellent onboarding experience and integration into the company, new colleagues will spend their first week onsite at one of our offices in Tennessee. Travel expenses will be paid. This is a requirement. Position Summary The Senior AI Developer Platform Engineer is responsible for designing, building, and maintaining the AI-augmented software delivery platform that enables Lirio's engineering team to build software faster and safer using AI coding agents. This role owns the end-to-end developer toolchain, from work item intake through AI agent coding loops to validated, compliant pull requests, ensuring that developers and AI coding agents can produce production-ready code together within Lirio's HIPAA/HITRUST-regulated environment. This is a developer platform role, not a product engineering role. The focus is entirely on accelerating how we build software: the tooling, agent workflows, compliance guardrails, CI/CD integrations, and developer experience that make every engineer on the team measurably more productive. While Lirio's product includes AI-powered capabilities (precision nudging, behavioral science models, engagement optimization), this role does not work on those product AI systems. Instead, it builds the platform and processes that the teams building those systems use to deliver faster and with higher quality. The Senior AI Developer Platform Engineer will collaborate cross-functionally with platform, cloud, security, and machine learning research engineers, as well as system architects, to ensure the AI developer platform integrates cleanly with Lirio's existing infrastructure and compliance posture. This role carries urgency. The advantage from AI-assisted development compounds over time, and this person needs to deliver working developer platform capabilities in weeks, not quarters, starting with what we have today and iterating based on real results. Essential Duties & Responsibilities AI Coding Tool Evaluation & Selection • Evaluate and recommend AI coding tools (Cursor, Claude Code, GitHub Copilot, Codex CLI, and emerging tools) against Lirio's developer workflows, compliance constraints, and codebase characteristics. • Conduct structured evaluations of new models and tools as they launch, testing against real coding tasks in our environment, not just vendor benchmarks. • Maintain the evaluation framework and tooling inventory, ensuring the team uses approved, security-reviewed tools on compliance-sensitive systems. Developer Harness Architecture & Implementation • Design and build the agent orchestration layer: instruction files (.cursor/rules/, AGENTS.md, CLAUDE.md), MCP connectors to Azure DevOps and/or GitHub, context packaging templates, and agent routing configurations. • Enable AI coding agents to execute multi-step software development tasks autonomously (decompose, plan, code, test, validate, and submit PRs) with quality gates at each phase and defined escalation points. • Design agent coordination patterns (planner-coder-reviewer, sub-agent delegation) and workflow state management for complex tasks that span multiple agent steps. • Define human escalation triggers so that when agents encounter ambiguity, scope boundaries, or compliance-sensitive decisions, the workflow surfaces the decision to a human rather than guessing. • Ensure AI coding agents receive the right context for each task type, including project conventions, compliance constraints, coding standards, and relevant codebase context. Manage context window budgets so agents maintain accuracy across large codebases. • Build and maintain work decomposition patterns and templates that structure work items for effective agent execution. • Architect integrations between the AI developer platform and the development ecosystem, including work item tracking, source control, CI/CD pipelines, and code review workflows, forming a coherent, automated delivery chain. Compliance Guardrails for AI-Generated Code • Build rules, instruction files, and CI pipeline checks that flag PHI exposure, tenant isolation concerns, and security issues in AI-genera