LaunchFamily is a mission-driven company that empowers families to take control of their children’s growth, learning, and well-being through intelligent systems. We’re building the world’s first AI-powered Family OS.
Parents juggle 50+ decisions a day, meal planning, homework help, emotional check-ins, and schedules. Most 'family apps' are just glorified to-do lists. We're building something different: an AI that actually understands your family's rhythm and proactively helps you stay ahead.
We’re looking for a Senior Software Engineer who can architect and scale the AI backbone behind this system, from retrieval-augmented generation (RAG) pipelines to multi-agent orchestration, and intelligent data flows that make our assistant truly personal.
This is an equity-only opportunity during the beta phase as we prepare for seed funding. Our founders have led and co-founded ventures that collectively raised over $100M and have had successful exits. You’ll be joining at the earliest stage to define the foundation of something transformative.
What You’ll Build
AI Infrastructure (40%)
- Design and implement multi-agent systems using the OpenAI Agents SDK for domains like scheduling, meal planning, education, and emotional guidance.
- Build RAG pipelines with hybrid search (vector + structured), using PostgreSQL + pgvector, Redis, and Embeddings APIs to ground AI responses in trusted family data.
- Develop contextual memory systems to store, retrieve, and rank user-specific insights (daily logs, family routines, past conversations).
- Experiment with function calling, tool-use orchestration, and chain-of-thought prompting to create agents that reason and collaborate.
- Optimize token usage, caching, and model routing to strike a balance between personalization, performance, and cost.
Core platform Engineering (30%)
- Design modular, scalable NestJS services (Fastify) with Drizzle ORM and PostgreSQL.
- Build multi-tenant APIs and workspace logic to support apps built on Launched (our low-code builder).
- Manage async workflows with BullMQ for real-time event processing, streaming responses, and queue-based pipelines.
- Maintain end-to-end type safety with shared TypeScript models across backend and frontend.
Frontend Portals (30%)
- Develop core interfaces for Launched, enabling creators to train and deploy AI chatbots, tools, and apps using the same infrastructure that powers LaunchFamily.
- Contribute to our Next.js-based assistant UI with real-time streaming, context management, and AI-driven visualizations.
- Collaborate with product to prototype new AI-driven experiences, from proactive notifications to visual family insights.
Tech Stack
AI Layer
- Agents SDK (core), LangChain / AutoGen (support)
- RAG Stack: PostgreSQL + pgvector, Redis, OpenAI Embeddings
- Model Integration: GPT-4o, custom fine-tuned models, retrieval interfaces
- Evaluation & Testing: structured outputs, JSON schema validation, prompt benchmarking
Core Platform
- Backend: NestJS (Fastify), TypeScript, Drizzle ORM, PostgreSQL
- Frontend: Next.js, TailwindCSS, WebSockets
- Infrastructure: Docker Compose, Railway / Vercel, CI/CD, Jest
What We’re Looking For
- 5+ years of full-stack engineering experience (TypeScript preferred)
- Strong knowledge of LLM integration, RAG systems, or AI agent frameworks
- Solid experience designing event-driven architectures and real-time systems
- Deep understanding of database design, query optimization, and data retrieval patterns
- Proficiency with prompt engineering, structured output design, and context management
- Experience deploying AI-based APIs in production environments
- A belief in simplicity, scalability, and testable design
- Passion for meaningful products that genuinely help families
Nice-to-Have
- Familiarity with LangGraph or AutoGPT
- Experience with voice, multimodal inputs, or personalized memory systems
- Prior work in consumer AI, health/wellness, or education platforms
- Startup or co-founder experience
Your Path Forward
This is a founding engineer role with a clear trajectory to technical leadership.
As we grow from beta → seed → Series A, you'll naturally evolve from hands-on architect to CTO or VP of Engineering — building and leading the team you wish you’d joined.
We’re not hiring someone to “fill a seat until we find a CTO.”
We’re hiring the person who becomes that CTO.
Why LaunchFamily
- Build with purpose, every feature helps real families live with less chaos and more connection.
- Work with experienced founders who have scaled and exited successful ventures.
- Be hands-on with cutting-edge AI, from architecture to agents.
- Fully remote and asynchronous, we value autonomy and craftsmanship.
- Earn meaningful equity in a venture positioned for growth and long-term social impact.
Compensation
This is an equity-only role until seed funding or milestone revenue. As we scale subscriptions, compensation will expand alongside shared success.
If you’re an AI-native engineer who thrives at the intersection of LLMs, data systems, and real-world impact, join us to build the foundation of the Family OS.