Peach Pilot - Founding Engineer

Peach Pilot: Founding Engineer Atlanta, GA (Buckhead) | Founding Team | In-office 3 days/week

Most AI companies sell tools. We transform how businesses run.

Peach Pilot builds a platform that ingests everything about how a company operates every system, every process, every signal and constructs a Company Brain: a living knowledge graph that connects people, decisions, and outcomes across the entire organization. We deploy 92 pre-built AI agents that work together across every business function, governed by humans at every critical step. The system gets smarter with every interaction.

We don't sell software licenses. We embed into a client's operation, learn their business in weeks, show them what's broken backed by their own data, and redesign their highest-impact business functions with AI. Our first vertical is insurance. Our first client engagement is already scoped and funded.

Peach Pilot is co-founded by Mario Montag (Predikto acquired by a Fortune 50; McKinsey, PwC) and JP James (Hive Financial Assets, Georgia Tech, TITAN 100). We have a working platform with live infrastructure and a proven data-to-insights methodology.

The Role

This is a founding team hire. You will be the primary hands-on technical contributor, working directly alongside Mario and JP to own the platform that powers everything we deliver to clients. This is a building role not a management role with occasional code reviews.

You will be leading a development team where AI agents are driving the build — not assisting it. This is a fundamental shift in how software is being developed, and it is how we are building from day one. If you've been waiting for the right environment to work this way, this is it.

In the early months, you will write code, make architecture decisions, and ship real capabilities. As the team grows, you will provide technical mentorship and guidance as a partner not a gatekeeper.

What You'll Solve

You aren't inheriting a roadmap — you are shaping the foundation. The hard problems you will tackle immediately include:

Data Ingestion at Scale: Connect to every system a client uses — CRM, email, calls, calendars, documents, chat, financial systems — through our Nango-based integration layer with 700+ connectors. Build custom pipelines for industry-specific systems. Ensure data quality through dedup, enrichment, classification, and validation before anything enters the knowledge graph.

The Company Brain: Architect and evolve a knowledge graph (Memgraph + Qdrant) that captures institutional knowledge — people, relationships, processes, decisions, and outcomes — across an entire organization. Build the Reasoning Engine that operates both strategically and operationally over this graph.

Agent Orchestration: Own the architecture for AI agents that coordinate across business functions. Build the coordination protocol, human-in-the-loop governance, and reinforcement learning loop where agents get smarter from every outcome.

Analysis Engine: Build the pipeline that ingests weeks of client data and surfaces findings the client didn't know about their own business alignment gaps, performance disparities, wasted effort, missed revenue. This is the moment that sells the engagement.

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 for the first client engagement.
• Make foundational architecture decisions across data ingestion, knowledge graph, and agent orchestration.
• Establish code standards, testing practices, and deployment pipelines.
• Build or refine the data ingestion pipelines that connect to the first client's systems.

Months 1–6: Build the Engine

• Knowledge Graph: Evolve the Memgraph + Qdrant architecture to handle industry-specific schemas, cross-system entity resolution, and temporal data patterns.
• Agent Runtime: Own the orchestration engine — agent lifecycle, context injection, task coordination, and the learning loop where outcomes feed back into agent behavior.
• Analysis Engine: Build the analysis pipeline that produces the narrative findings and visual dashboards clients see.
• Multi-Model Routing: Optimize LLM usage across Claude, GPT, and open-source models with cost-aware task allocation through LiteLLM.
• Client Delivery Infrastructure: Ensure the platform can be deployed into a new client environment reliably — multi-tenant isolation, data security, and repeatable setup.

Ongoing: Team & Client Impact

• Provide technical guidance to the QA Engineer, Full-Stack Engineer, and future hires as a partner raising the bar.
• Participate in client technical discovery sessions to understand their systems, data landscape, and integration requirements.
• Translate complex architecture decisions into clear language that builds trust with clients and co-founders.
• Contribute to the transformation methodology what we learn from each engagement should make the platform and the process better for the next one.

Who You Are

• A Decade (or More) Deep — and Still in the Code. You are the technical anchor this team is built around. Ten-plus years of hands-on engineering, architecture decisions, and shipped products — not from the sidelines, but in it. If that's you, you'll feel at home here.
• A True Zero-to-One Builder. You have taken a platform from nothing to production and scaled it. This is our primary filter.
• An AI/ML Expert. You have shipped production AI systems that real users depend on. You understand LLM orchestration, embeddings, vector search, and agent coordination. You've worked with knowledge graphs or data-intensive applications where the data model is as important as the code.
• A Player-Coach. You are comfortable as both an architect and a deep individual contributor. You will ship code, review PRs, debug pipelines, and own outcomes alongside your team.
• A Clear Communicator. You can translate complex technical decisions into language that builds trust with non-technical co-founders and enterprise clients. You're comfortable in a client-facing room when the conversation turns technical.
• Startup-Tested. You've been in an early-stage environment before. You know what it feels like to build something from nothing — and you're energized by it.

The Stack

AI/LLM: Anthropic Claude · OpenAI GPT · LiteLLM (multi-model routing) · Custom agent orchestration with reinforcement learning Backend: Python (FastAPI) · Async agent runtime · JWT auth + multi-tenant isolation · Pydantic Data & Graph: Memgraph · Qdrant · PostgreSQL · Redis Integrations: Nango (700+ connectors) Infrastructure: Google Cloud Platform (Cloud Run, GCE, Firebase) · Azure (Cosmos DB, AI Search) · GitHub Actions CI/CD · Docker

We are cloud-agnostic across GCP and Azure. The right hire will help shape how we deploy and scale across both.

What Makes This Different

You are joining a proven founder's second company with established domain credibility. We have a working platform with live infrastructure and a first client engagement already in motion. You will have access to production data, live workflows, and real compliance requirements from day one.

Every engagement makes the platform smarter. Every client's data enriches the knowledge base for the next one. You're not building features for a backlog — you're building the engine that transforms how companies operate.

We pay market rates and offer meaningful founding-team equity.

The clincher: Tell us about a platform you built from zero to one — what you built, what broke, and what you learned.