Engineering Manager — AI-First Platform & Agent Teams

<div class="content-intro"><p data-start="216" data-end="234"><strong data-start="216" data-end="234">About LumiMeds</strong></p> <p data-start="251" data-end="466">LumiMeds is a fast-growing U.S.-based telehealth startup focused on weight management and long-term metabolic health. We are building the next generation of e-commerce and clinical infrastructure from the ground up.</p> <p data-start="468" data-end="684">As an early-stage company, we move quickly, operate with limited layers, and expect high ownership from every team member. There is no bureaucracy here — decisions happen fast, priorities evolve, and builders thrive.</p> <p data-start="686" data-end="834">We are a remote-first, globally distributed team that values clarity, accountability, and people who take initiative rather than wait for direction.</p></div><p><strong>Platform &amp; Product Engineering — LumiMeds</strong><br> <strong>Location:</strong> Remote — partial US hours overlap required (minimum 4–5 hours daily overlap with US Pacific/Eastern)<br> <strong>Seniority:</strong> Manager — Player/Coach</p> <h2>What We're Building</h2> <p>LumiMeds is a high-growth telehealth platform building the operating system for modern virtual care — an AI-accelerated clinical engine, a high-converting e-commerce storefront, a consumer mobile app, and intake infrastructure that moves at the speed our patients expect.</p> <p>We don't scale engineering by adding headcount. We scale by multiplying leverage — through better systems, better tooling, and better use of AI. Our engineers already orchestrate Claude agent teams in production. Your job is to raise the ceiling on what that means.</p> <h2>The Role</h2> <p>This is a player/coach role for an engineer-turned-manager who is serious about AI-native engineering. You will lead a team of 4–8 full-stack engineers and simultaneously operate as the team's resident expert in designing and running <strong>Claude agent teams</strong> — using coordinated AI agents as a structural force multiplier on engineering output.</p> <p>You are not here to run standups and update Jira. You are here to build a team that ships more, faster, at higher quality than any team its size should be able to — by treating AI agent orchestration as a first-class engineering discipline. You will spend roughly <strong>40% of your time coding and in agent pipelines</strong>, and 60% managing, designing systems, and raising the team's AI literacy.</p> <h2>What Makes This Role Different</h2> <p>Most engineering managers run teams of humans. You will run a team of humans <strong>and</strong> a fleet of agents — and your ability to design, direct, and verify agent work is as important as your ability to manage people.</p> <p>We are not looking for someone who has used Claude or experimented with agents. We need someone who has built real agent pipelines under production pressure — who knows exactly where they break, how to recover, and how to design for reliability at scale. This is the core of the role.</p> <ul> <li>Break complex engineering initiatives into agent-executable subtasks with crisp acceptance criteria</li> <li>Design multi-agent pipelines — parallel subagents for feature branches, test generation, code review, and documentation — and stitch their outputs into production-ready deliverables</li> <li>Set the team's standards for when to use agents, how to prompt them effectively, how to verify their outputs, and when to override them</li> <li>Treat agent output as team output — you are accountable for everything the agents on your team produce</li> <li>Continuously raise the ceiling: as the models improve, you update the playbook</li> </ul> <h2>What You'll Actually Do</h2> <p><strong>Lead and grow a high-performing engineering team.</strong> Hire, onboard, coach, and develop 4–8 engineers. Set clear expectations, give direct feedback, and build a culture where velocity and quality are not in tension.</p> <p><strong>Design and operate Claude agent teams.</strong> Architect agent pipelines using the <strong>Claude Agent SDK</strong> to parallelize engineering work at scale — parallel feature development, automated test coverage, documentation generation, code review passes, and spec-to-implementation workflows. You know how to define subagent roles, manage inter-agent context handoffs, validate outputs, and escalate to human judgment at the right moments.</p> <p><strong>Stay in the code.</strong> You are a working engineer. You write production code, review PRs with technical depth, debug hard problems, and pair with engineers on the work that needs a senior eye. AI augments your output — it does not replace your technical judgment.</p> <p><strong>Set the AI velocity standard.</strong> Define how the team uses AI tooling — Cursor, Claude Code, agent pipelines — and push the frontier. You have strong, specific opinions about how to prompt effectively, which tasks to delegate to agents, and how to verify agent output before it ships.</p> <p><strong>Own delivery end to end.</strong> Run sprint planning, resolve blockers, manage dependencies across product, clinical, and infrastructure. You own outcomes — not just process.</p> <p><strong>Write tickets AI agents can execute.</strong> Your specs are precise, structured, and unambiguous — acceptance criteria, edge cases, API contracts, all present. Claude Code or a junior engineer can run with them without a sync. Your specs don't loop.</p> <p><strong>Build and own consumer app and e-commerce systems.</strong> You've shipped full-stack consumer products end to end — mobile-backed apps, e-commerce storefronts, subscription billing, checkout flows. You understand high-conversion funnel architecture and have built or owned user behavior tracking infrastructure: event schemas, analytics pipelines, conversion funnels, retention dashboards. This is not adjacent to the role — it is the role.</p> <p><strong>Build and own A/B testing infrastructure.</strong> Design and maintain the experimentation platform that powers product decisions — feature flags, experiment assignment, statistical significance tracking, and results dashboards. You've built this before for high-traffic web products. You understand holdout groups, novelty effects, and how to run clean experiments across checkout flows, onboarding, and clinical intake.</p> <p><strong>Build the systems that make the team scale.</strong> Engineering standards, PR review norms, deployment practices, observability, incident response. You build the scaffolding once so the team doesn't rebuild it repeatedly.</p> <p><strong>Collaborate cross-functionally.</strong> Partner with Product, Clinical, and Ops to translate requirements into engineering reality. You are the technical voice in roadmap conversations — not a scheduler, but a decision-maker.</p> <h2>What You'll Own</h2> <table> <tbody><tr><th>Domain</th><th>Scope</th></tr> <tr><td>Engineering Team</td><td>4–8 full-stack engineers — hiring, performance, growth</td></tr> <tr><td>Agent Team Operations</td><td>Claude agent pipelines for parallelized engineering work</td></tr> <tr><td>Delivery</td><td>Sprint execution, unblocking, cross-functional coordination</td></tr> <tr><td>Technical Standards</td><td>Code quality, PR norms, AI tooling standards, observability</td></tr> <tr><td>Core Platform</td><td>Clinical engine, e-commerce, subscription billing, mobile backend</td></tr> <tr><td>A/B Testing Platform</td><td>Experimentation infrastructure, feature flags, statistical tracking</td></tr> <tr><td>AI Infrastructure</td><td>LLM integration patterns, agent orchestration architecture</td></tr> </tbody></table> <h2>Required Skills &amp; Experience</h2> <p><strong>Engineering Leadership:</strong></p> <ul> <li>6+ years of software engineering experience, including 2+ years in a lead or management role</li> <li>Hands-on experience with <strong>Node.js / TypeScript</strong> backends and <strong>Next.js / React</strong> frontends — you can read, write, and review production code at a senior level</li> <li>Strong database fundamentals: <strong>PostgreSQL</strong> (schema design, migrations, query optimization), Redis</li> </ul> <p><strong>AI-Native Engineering (Non-negotiable):</strong></p> <ul> <li><strong>Claude Agent SDK:</strong> Demonstrated experience building and orchestrating multi-agent pipelines — decomposing tasks, defining subagent roles, managing context handoffs, validating agent output</li> <li><strong>LLM Integration:</strong> Production experience integrating LLMs into real systems — streaming, tool use, structured outputs, prompt engineering</li> <li><strong>AI Dev Tooling:</strong> Daily use of Claude Code, Cursor, or equivalent. You have built workflows around these tools, not just used them ad hoc</li> <li>You can articulate — with specificity — how agent orchestration changes what a small engineering team can ship</li> </ul> <p><strong>Experimentation &amp; A/B Testing:</strong></p> <ul> <li>Proven experience designing and building web A/B testing platforms from the ground up — not just using third-party tools, but owning the infrastructure</li> <li>Deep understanding of experiment design: randomization, assignment consistency, statistical power, holdout groups, and avoiding novelty bias</li> <li>Experience running experiments across high-traffic consumer funnels (checkout, onboarding, pricing, landing pages)</li> <li>Familiarity with feature flag systems (LaunchDarkly, Statsig, homegrown) and experimentation analytics pipelines</li> </ul> <p><strong>Consumer Product &amp; Tracking:</strong></p> <ul> <li>Hands-on experience building consumer apps and e-commerce platforms end to end — storefronts, checkout, subscriptions, billing</li> <li>Built user behavior tracking infrastructure: event schemas, analytics pipelines, conversion funnels, retention analysis</li> <li>Familiarity with tools like Segment, Mixpanel, Amplitude, or equivalent homegrown tracking systems</li> </ul> <p><strong>Systems &amp; Delivery:</strong></p> <ul> <li>Experience running engineering sprints, managing dependencies, and owning delivery timelines</li> <li>Ability to write engineering specs that AI coding agents and engineers can execute with minimal back-and-forth</li> <li>Familiarity with <strong>AWS</strong> (EC2, RDS, Lambda, S3), Vercel, GitHub Actions, and CI/CD pipelines</li> </ul> <p><strong>Compliance:</strong></p> <ul> <li>Working knowledge of HIPAA/SOC2 requirements — you understand how compliance shapes architecture decisions</li> </ul> <p><strong>English:</strong></p> <ul> <li>Fluent written and spoken English — all team communication is async in English (Slack, PRs, specs, docs)</li> </ul> <h2>Candidate Qualifications</h2> <ul> <li><strong>The player/coach instinct:</strong> You want to manage, but you're not ready to stop building. You think leaving code entirely would make you a worse manager.</li> <li><strong>AI-native, provably so:</strong> You can show, concretely, how agent orchestration has changed your own output — examples, numbers, or a portfolio. Not just familiarity — results.</li> <li><strong>High standards for output quality:</strong> AI-generated code is your code. You are not the manager who merges anything that compiles. You have a verification practice.</li> <li><strong>Direct communicator:</strong> You give feedback clearly, make decisions without excessive consensus-building, and disagree with product or leadership when the technical reality demands it.</li> <li><strong>High agency:</strong> You identify problems, propose solutions, and execute — you don't wait to be managed.</li> </ul> <h2>Nice to Have</h2> <ul> <li>Experience in telehealth, DTC health, or a regulated healthcare environment</li> <li>You've built an internal agent framework or tooling layer that other engineers on your team used</li> <li>Shipped a consumer mobile app with measurable retention and a backend you owned</li> <li>Background in distributed systems or real-time infrastructure (WebRTC, event-driven architectures)</li> <li>You've written a post, given a talk, or built something in public about AI-augmented engineering</li> </ul> <h2>Why LumiMeds</h2> <p><strong>AI as infrastructure, not a feature.</strong> We've already rewired how we build around AI. You won't be evangelizing something new — you'll be operating at the frontier with a team that's already bought in.</p> <p><strong>Real technical complexity.</strong> Clinical state machines, real-time patient-provider flows, high-stakes billing, HIPAA. The problems are hard because the domain is hard.</p> <p><strong>Small team, enormous leverage.</strong> You won't manage through layers. Your decisions show up in production the same week.</p> <p><strong>Direct impact.</strong> The systems you build affect patient outcomes. That's not a cliché here — it's the constraint that makes the work matter.</p><div class="content-conclusion"><p data-start="726" data-end="742"><strong data-start="726" data-end="742">How to Apply</strong></p> <p data-start="744" data-end="911">If this role sounds like a fit, we’d love to hear from you. Please submit your application in English and ensure your resume reflects relevant experience for the role.</p> <p data-start="913" data-end="1074">This position is open to candidates based in approved locations, depending on the role and business needs. Qualified applicants will be contacted for next steps.</p> <p data-start="1076" data-end="1186">LumiMeds is an equal opportunity employer. We hire based on skills, experience, and alignment with our values.</p> <p data-start="1076" data-end="1186"><em>Please note: This role requires professional-level English communication and availability to work U.S. business hours.</em></p></div>