Peach Pilot - Founding Engineer

Hive Financial Systems•Atlanta, GA

2d•Hybrid

About The Position

Peach Pilot - Founding Engineer Atlanta, GA (Buckhead) | Founding Team | In-office 3 days/week Enterprise AI transformation fails at the human layer, not the technology layer. Every AI vendor sells capability. Nobody sells trust and adoption. Peach Pilot does. We are building an enterprise AI operating system comprised of three interconnected technologies: Personal AI Chief of Staff: A working partner for every employee that automates tasks and surfaces priorities. Hyper-Personalized Behavioral Intelligence: AI that learns communication styles and adapts in real-time to earn user trust. Organizational Intelligence Layer: A living knowledge graph that helps leadership see around corners and flag risks early. Peach Pilot is a funded startup co-founded by Mario Montag (Predikto, McKinsey, PwC) and JP James (Hive Financial, Georgia Tech). We pair our platform with Forward Deployed Engineers to ensure adoption is real. The Role This is a founding team hire. You will be the primary hands-on technical contributor, working directly alongside Mario and JP to architect and build the platform from the ground up. This is a building role. In the early months, you will write code, own architecture decisions, and ship real features. You will also serve as a technical anchor for a small team providing mentorship and technical guidance as a partner. The Challenge (What You’ll Solve) You aren’t inheriting a roadmap; you are architecting the foundation. The hard problems you will tackle immediately include: Agent Orchestration: Moving beyond single-model calls to complex, multi-agent coordination that survives the 6-month model replacement cycle. Structural Governance: Designing “Governance Agents” that act as a hard-coded audit trail for “Execution Agents.” The Context Problem: Building a self-organizing knowledge graph using Neo4j and vector search that captures institutional memory without manual data entry. What You Will Own & Deliver First 90 Days: Lay the Foundation Work directly with Mario and JP to assess the current platform and prioritize the build-out. Make foundational architecture decisions and begin building the core AI operating system. Establish code standards, testing practices, and deployment pipelines alongside the existing team. Months 1–6: Build the Operating System Orchestration: Own the architecture for interconnected agent orchestration and shared context layers. Governance: Design structurally separate execution and governance agents with full human-override capabilities. Intelligence: Architect the Enterprise Knowledge Graph (Neo4j + vector search) to capture institutional memory. Optimization: Implement multi-model routing across LLM providers (Claude, GPT-4o, Grok) with cost-optimized task allocation. Ongoing: Team & Customer Provide technical guidance to the QA Lead, Full-Stack Engineer, and interns — as a partner raising the technical bar. Engage directly with enterprise customers in technical discovery, implementation planning, and onboarding sessions alongside the founding team. Translate complex architecture into clear, credible language that builds customer trust. Who You Are The Builder: You have built a platform from zero to one and scaled it. This is our primary filter. The AI/ML Expert: You have shipped production AI systems that real users depend on. You understand LLM orchestration, embeddings, and vector search. The Player-Coach: You are comfortable as both an architect and a deep individual contributor. You will ship code, review PRs, and debug pipelines alongside your team. The Communicator: You can translate complex technical decisions into language that builds trust with non-technical co-founders and enterprise stakeholders alike. The Technical Anchor: You know how to be available to a small team — mentoring without micromanaging, guiding without gatekeeping — while staying deep in your own work. Prior Startup Experience: Ideally, you’ve been in an early-stage environment before. You know what it feels like to build something from nothing. The Stack: Azure (Cosmos DB, AI Search), Anthropic Claude, OpenAI GPT-4o, xAI Grok, Neo4j, Snowflake, Python, TypeScript, and OpenClaw. What Makes This Different You are joining a proven founder’s second company with established domain credibility. Through strategic relationships with sister companies in insurance, payments, and lending, you will have access to production data, live workflows, and real compliance requirements from day one. We pay market rates and offer meaningful founding-team equity. The clincher: Please tell us about a platform you built from zero to one: what you built, what broke, and what you learned.

Requirements

You have built a platform from zero to one and scaled it. This is our primary filter.
You have shipped production AI systems that real users depend on. You understand LLM orchestration, embeddings, and vector search.
You are comfortable as both an architect and a deep individual contributor. You will ship code, review PRs, and debug pipelines alongside your team.
You can translate complex technical decisions into language that builds trust with non-technical co-founders and enterprise stakeholders alike.
You know how to be available to a small team — mentoring without micromanaging, guiding without gatekeeping — while staying deep in your own work.

Nice To Haves

Ideally, you’ve been in an early-stage environment before. You know what it feels like to build something from nothing.

Responsibilities

Work directly with Mario and JP to assess the current platform and prioritize the build-out.
Make foundational architecture decisions and begin building the core AI operating system.
Establish code standards, testing practices, and deployment pipelines alongside the existing team.
Own the architecture for interconnected agent orchestration and shared context layers.
Design structurally separate execution and governance agents with full human-override capabilities.
Architect the Enterprise Knowledge Graph (Neo4j + vector search) to capture institutional memory.
Implement multi-model routing across LLM providers (Claude, GPT-4o, Grok) with cost-optimized task allocation.
Provide technical guidance to the QA Lead, Full-Stack Engineer, and interns — as a partner raising the technical bar.
Engage directly with enterprise customers in technical discovery, implementation planning, and onboarding sessions alongside the founding team.
Translate complex architecture into clear, credible language that builds customer trust.