The Mission

We're building an AI-powered insurance brokerage that's transforming the $900 billion commercial insurance market by automating processes that currently run on pre-internet systems. Fresh off our $8M seed round, we're looking for an exceptional AI Platform Engineer who can architect and develop the core infrastructure that powers our entire AI ecosystem.

You'll build the foundational platform that enables our AI agents to operate across growth, sales, operations, and customer service. This includes extending our proprietary AI Grid context engineering system, developing evaluation infrastructure, building ML models for market-making and reasoning, and creating the systems that enable massive operational leverage (enabling one person to do the work of thousands). You'll be responsible for both ambient agents (background processes with context/memory) and the core systems that enable frontier agents (human-AI interfaces) to deliver exceptional experiences.

We're committed to "Staying REAL" with our AI systems - building agents that are Reliable, Experience-focused, Accurate, and have Low latency. You will work directly with the CEO and CTO to execute on our AI vision with a bias toward action. We live by core principles: "There is no try, there is just do," "Actions lead to information, always default to action," and "Strong opinions lead to information." We need engineers who build and ship, not just plan and strategize.

Outcomes You'll Drive

Extend and enhance our proprietary AI Grid context engineering system that combines ETL with LLM pipelines and graphs
Build robust evaluation systems with datasets and human-annotated data for supervised fine-tuning (SFT) and reinforcement learning (RL)
Develop ML models for critical systems including underwriter load balancing (our market-making engine) and reasoning systems
Architect and maintain data pipelines that pull from multiple diverse sources and push to various destination systems (ClickHouse, vector databases, ML platforms, etc.)
Build MCP (Model Context Protocol) servers that expose memory and tools to AI agents across the platform
Create integrations with payment providers and financial systems for seamless transaction processing
Develop growth engineering infrastructure including agents that determine campaign strategies and optimize outreach
Build voice AI systems for follow-ups, information collection, and cold outbound campaigns
Create customer service AI infrastructure enabling one person to manage thousands of leads and customers
Design ETL/ELT pipelines that handle both batch and real-time processing at scale
Implement Lambda architecture patterns combining event streaming with batch processing
Partner with forward deployed engineers to ensure platform capabilities meet business needs
Build comprehensive observability systems to monitor agent reliability and performance

You're Our Person If

You're exceptional at one or more of: distributed systems, AI agents, context engineering, or data engineering
You have experience building evaluation systems and working with human-annotated datasets for ML training
You understand how to build ML models for complex systems like market-making and reasoning engines
You have deep expertise with modern data warehouse and ML platforms (Databricks, Astronomer, or similar)
You can architect MCP servers and understand how to expose memory and tools to AI systems
You have experience with payment provider integrations and financial systems
You understand how to build voice AI infrastructure for outbound campaigns and information collection
You can architect systems that enable massive operational leverage (1:1000s ratios)
You have experience with data enrichment and building DAG-based orchestration systems
You understand CAP theorem tradeoffs and can make appropriate architectural decisions
You're equally comfortable with TypeScript/Node.js and Python/ML frameworks
You ship features daily and take immediate action instead of overthinking
You embrace "there is no try, there is just do" as your engineering mantra

Hard Requirements

Strong experience with both TypeScript/Node.js and Python
Deep understanding of distributed systems principles, CAP theorem tradeoffs, and event sourcing architecture
Experience with modern data warehouse solutions (Databricks, Astronomer, Snowflake, or similar)
Proven track record building ML modeling infrastructure and ETL/ELT pipelines
Experience with evaluation systems and human-annotated datasets for ML training
Experience building ML models for complex systems (recommendation engines, market-making, reasoning)
Experience with MCP server architecture and protocol implementation
Experience with voice AI systems and conversational interfaces
Experience with payment provider integrations and financial systems
Experience designing data pipelines that serve multiple destination systems
Experience with temporal.io workflows or similar durable execution frameworks
Experience with data enrichment and DAG-based orchestration
Proven track record building production AI/ML systems at scale
Experience with vector databases (Qdrant, Pinecone, Weaviate) and RAG systems
Strong understanding of context engineering for AI systems
Advanced usage of Cursor or WindSurf coding IDE
Must be based in San Francisco and work in-office 5.5 days per week (relocation assistance provided)

Our Tech Stack

AI Agent Infrastructure:

AI Grid - our proprietary context engineering system combining ETL with LLM pipelines and graphs
Temporal.io for durable workflow orchestration across agent systems
Pydantic-AI for type-safe agent development with structured validation
MCP servers for exposing memory and tools to AI agents
Evaluation systems with human-annotated datasets for SFT and RL
Event sourcing architecture with Redis streams and PostgreSQL
Lambda architecture combining real-time event streams and batch processing
RAG systems with rigorous evaluation frameworks
Claude (Anthropic), GPT-4 (OpenAI), and select open source models
Voice AI infrastructure for campaigns and customer interactions
Logfire for comprehensive agent observability

Data & ML Infrastructure:

Modern data warehouse solutions (Databricks/Astronomer) for ML modeling and ETL
ML models for underwriter load balancing (market-making) and reasoning systems
Evaluation infrastructure with human-annotated datasets for SFT/RL
Multiple destination systems including ClickHouse for analytics
Apache Airflow, Temporal, Airbyte, and N8N for pipeline orchestration
Vector databases for AI context storage and retrieval
Custom data enrichment pipelines for growth engineering
Payment provider integrations for transaction processing
PostHog for product analytics and event tracking
Redis streams and PostgreSQL for operational data

Core Engineering:

TypeScript/Node.js for robust application development
Python for AI systems and ML workflows
Next.js/React for frontend experiences
Event-driven architecture with distributed systems design

What You'll Build in Your First 90 Days

First Month:

Extend and enhance our AI Grid context engineering system with new capabilities
Build initial evaluation datasets and implement human annotation workflows
Set up MCP servers for memory and tool exposure across AI agents
Create voice AI infrastructure for outbound campaigns and information collection
Design ML models for underwriter load balancing and reasoning systems
Establish comprehensive observability and monitoring systems

Second Month:

Develop sophisticated data enrichment pipelines for growth engineering
Build agents that determine and optimize campaign strategies
Implement payment provider integrations for seamless transactions
Expand evaluation systems with automated dataset generation
Create customer service AI infrastructure for 1:1000s operational leverage
Implement advanced orchestration patterns for complex workflows

Third Month:

Scale AI Grid to handle increasing complexity and volume
Optimize ML models for market-making and reasoning performance
Build comprehensive growth engineering platform with campaign automation
Implement advanced voice AI features for cold outbound and follow-ups
Fine-tune models using human-annotated datasets (SFT/RL)
Integrate all systems into a unified, observable platform architecture

Our AI Philosophy

Context is King: The quality of AI decisions directly correlates with the richness of available context through AI Grid
10x Platform Impact: Build infrastructure that enables forward deployed engineers to create 10x business leverage
Evaluation-Driven Development: Use human-annotated data and rigorous evaluation to continuously improve
Multi-System Integration: Design for multiple sources and destinations from day one
Event-Driven Architecture: React to events and state changes for maximum responsiveness
Distributed & Durable: Create fault-tolerant systems that maintain state and recover from failures
Business-Enabling Infrastructure: Every platform capability should unlock new business opportunities
Action Orientation: Always default to action - ship code, gather data, and iterate
Execution Focus: There is no try, there is just do - we value engineers who build and ship

Join Us To Transform the $900B Insurance Market

This is an early-stage role at a fast-moving startup, and you'll often experience the crawl-walk-run approach to building. You'll quickly prototype systems and then push them into productionized platforms that can scale. We're looking for people who can be creative in providing impact first, then take learnings from that impact and push them back into the system.

You should ideally have worked in an early-stage startup environment and understand the pacing. This is a fast-paced environment where we value ownership and quick, rapid feedback loops within the team. You'll work directly with the CEO and CTO to execute on our AI vision with a bias toward action.

We require you to be in San Francisco and work from our office 5.5 days per week. We'll cover relocation costs and believe the best teams collaborate intensively in person.

Skills

TypeScript, Node.js, Python, Distributed Systems, Context Engineering, AI Grid, Data Engineering, Databricks, Astronomer, ETL/ELT, ML Infrastructure, Data Enrichment, DAG Orchestration, Temporal.io, Pydantic-AI, MCP Servers, Evaluation Systems, SFT/RL, Voice AI, Payment Integration, Event Sourcing, CAP Theorem, Lambda Architecture, Apache Airflow, Vector Databases, RAG Systems, Redis Streams, PostgreSQL, AI Agent Development, System Architecture, Market-Making Systems, Reasoning Engines

AI Platform Engineer