AI Platform Engineer

Harper•San Francisco, CA

5d•Onsite

About The Position

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.

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)

Nice To Haves

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

Responsibilities

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