Principal Full Stack Engineer / Fractional CTO for AI Data and Media Platform $$$$
Summary
We are seeking a Principal Full Stack Engineer with extensive experience to develop and own core features for an AI-driven data and media platform, focusing on
backend, frontend, data workflows, and system design.
General Information
The platform integrates data ingestion pipelines, graph workflows, LLM-driven agent chains, media generation, and copilot experiences. The environment is early-stage, emphasizing rapid iteration, collaboration, and high engineering standards.
Tasks and Deliverables
- Develop and deploy production SaaS features including agent systems, GraphRAG, DAG visualizations, and data trees
- Integrate AI and media tools such as Claude Sonnet, FAL.ai, and Remotion
- Lead frontend development using React, Vite, TypeScript, TanStack Router/Query, Tailwind, and shadcn/ui
- Design backend architecture with Python, FastAPI, CopilotKit, and PydanticAI
- Model data and graph workflows with Neo4j and PostgreSQL
- Build APIs and integrations for agent workflows, AI generation, and DAG control
- Implement data ingestion pipelines for formats like GEDCOM, images, and PDFs, managing data variability
- Architect and develop graph visualization interactions with GoJS
- Enhance system reliability, observability, and performance across the stack
- Make technical decisions, simplify system complexity, and establish engineering standards
- Support future features including OCR, multi-agent pipelines, and structured data parsing
- Deliverables include ingestion pipelines for unified searches, metadata parsing, deduplication, auto-tagging, and verification engines for confidence scoring, duplicate detection, conflict flagging, and report generation within the copilot interface
Required Experience
- Required: 10+ years of full-stack software engineering experience with ownership of distributed or multi-service systems
- Required: Proven experience designing, running, and managing multi-agent AI systems or agent swarms (e.g. CrewAI, LangGraph, AutoGen, or equivalent)
- Required: Strong proficiency in Python, FastAPI, and PydanticAI for backend development
- Required: Strong proficiency in React, TypeScript, Vite, TanStack Router/Query, Tailwind, and shadcn/ui for frontend development
- Required: Strong experience with graph data models, Neo4j, and PostgreSQL performance optimization
- Required: Experience building ETL/ingestion pipelines handling messy or inconsistent data
- Required: Proven ability to design agent-driven or LLM-powered workflows (Claude, CopilotKit, or equivalent)
- Required: Experience with AI/ML integrations and media generation tools (e.g. FAL.ai, Remotion, or equivalent)
- Required: Experience with AWS cloud infrastructure (Lambda, S3)
- Required: Ability to simplify complex UX and data flows for end-users
- Required: Strong judgment around system boundaries, interfaces, and maintainability
- Nice to have: Experience with graph visualization libraries (GoJS) and GEDCOM or genealogy data formats
Required skills experience
| Python | 10 years |
| FastAPI | 5 years |
| PostgreSQL | 5 years |
| AWS Lambda | 5 years |
| D3.js | 5 years |
| LangChain / LangGraph / LangSmith | 5 years |
| Vite | 5 years |
| TanStack Query | 5 years |
| Shadcn UI | 5 years |
| Neo4j | 5 years |
| AWS S3 | 5 years |
| Pydantic | 5 years |
| TypeScript | 5 years |
Required languages
| English | C1 - Advanced |