Full-Stack Engineer (AI Product + Client Solutions)

Emberos•Los Angeles, CA

About The Position

We’re looking for a Full-Stack Engineer, AI Product & Client Solutions who can truly own and ship product end-to-end across frontend, backend, and data layers without needing constant oversight. You’ll be responsible for architecting and delivering systems that power our Brand Knowledge Graph, building interfaces that make complex enterprise data intuitive, and developing the LLM orchestration layer so it runs efficiently and reliably at scale. Equally important, you’re comfortable operating autonomously and taking full ownership from concept through deployment. You can build it, explain it, demo it, and defend the technical decisions behind it, translating complex systems into clear narratives for clients without needing to be managed step-by-step.

Requirements

5+ years of software engineering experience in fast-moving, high-performance environments
Strong full-stack engineering experience -- you have shipped real products end-to-end, not just maintained existing ones
Comfortable operating in client-facing settings. With an ability to clearly explain technical architecture, AI methodology, and product decisions to non-technical stakeholders with confidence.
Deep hands-on experience with Neo4j and graph data modeling
Practical experience integrating LLMs and building production-grade API integrations with AI platforms
Ability to design systems that avoid constant LLM calls and manage cost, latency, and quality tradeoffs
Proficient in React, TypeScript, Node.js, and modern frontend and backend frameworks
Experience designing and working with scalable databases and APIs
Clear, confident communicator who is energized by client interaction -- not just tolerant of it. With the ability to lead technical demos, respond to live client questions, and translate complex systems into clear business value narratives.

Nice To Haves

Experience with applied data science, ML-adjacent systems, or experimentation frameworks
Background in AI search, recommendation systems, SEO-like ranking models, or similar
Practical agent orchestration experience - deterministic, evaluable, production flows
Familiarity with conversational commerce or AI-powered transactional flows
Experience working on creative or content-driven platforms

Responsibilities

Develop and extend our Brand Knowledge Graph in Neo4j: modeling how changes to one node propagate and affect AI visibility and recommendations elsewhere
Build predictive optimization systems that model how specific content and strategy changes impact AI visibility outcomes
Design measurement and feedback loops that connect changes to outcomes and track predicted vs. actual lift over time
Implement scoring logic including Share-of-Prompt, accuracy measurement, sentiment analysis, and competitor mention detection
Analyze how optimizations at scale affect long-term LLM behavior and ecosystem dynamics
Build and maintain integrations with LLM platforms including ChatGPT, Claude, Grok, Perplexity, DeepSeek, and others as they emerge
Design orchestration systems that minimize unnecessary LLM calls: managing cost, latency, and quality tradeoffs intelligently
Develop agent-based analysis workflows that evaluate multiple optimization scenarios in parallel and forecast impact
Compare and stress-test multiple optimization strategies simultaneously to surface the most effective approaches
Build and ship full-stack features across frontend, backend, and data layers: from idea to production
Develop high-quality frontend interfaces in React and TypeScript that translate complex graph and model outputs into actionable insights for users
Design and optimize backend systems for performance, security, and scalability
Build workflow and tracking infrastructure recording what changed, why it changed, and the outcome -- integrating with Jira, Slack, HubSpot, and email
Lay foundations for AI-native commerce experiences where merchants can transact directly inside AI chat
Work closely with design and product to translate ideas into polished, production-ready experiences
Participate actively in client calls, demos, and technical conversations -- explaining systems clearly to non-technical enterprise stakeholders
Own QA processes and fix pack delivery: building test coverage, triaging bugs, and maintaining data integrity across the platform
Pull insights from complex datasets and translate them into findings that clients and internal teams can act on
Document architecture, decisions, and systems to support a growing team and future CTO onboarding