About Babs
Babs is building the smart operating system for modern families. Most AI tools are designed for work life, but managing home life is its own full-time job filled with coordination, communication, and constant context switching. Babs acts as a second brain that brings order to everyday life by connecting calendars, tasks, and messages into one intelligent system.
Our edge is in our ability to make complex systems feel simple. Our strength is our team — driven, thoughtful builders united by a mission to bring order to everyday life and give people the clarity of an organized mind. Our mission is to give people the power to live organized lives and organized minds. Our vision is to build joyful, connected communities. That begins with creating systems and workflows that help people feel more present and effective in their daily lives. When households run smoothly, they have more capacity to connect, contribute, and strengthen their communities.
The Role
We’re looking for an Founding AI Engineer to design, build, and scale the intelligence layer that powers Babs. You’ll work on the infrastructure that connects large language models, vector databases, and real-world data into a seamless, adaptive system.
This role sits at the intersection of machine learning infrastructure, data systems, and applied product engineering. You’ll be responsible for how Babs learns, remembers, and improves — turning context into intelligence and feedback into reinforcement.
You’ll help us move from AI-assisted features to a truly AI-native product that feels personal, contextual, and trustworthy.
What You’ll Do
- Design and implement retrieval and memory systems using vector databases and semantic search
- Build and maintain RAG pipelines that combine structured and unstructured data
- Develop feedback loops and evaluation systems to measure and improve model output quality
- Explore reinforcement learning (RL) and fine-tuning approaches that adapt model behavior to user context
- Integrate and experiment with multiple LLMs and APIs, choosing the right tool for each task
- Collaborate with platform and product engineers to bring intelligence into real features
- Create observability and evaluation systems for AI latency, accuracy, and reliability
- Contribute to architectural decisions that shape Babs’ long-term AI infrastructure
Our Ideal Candidate Has
- 4 or more years of experience working with LLMs, machine learning infrastructure, or applied AI systems
- Strong experience with Python and frameworks like LangChain, LlamaIndex, or equivalent orchestration tools
- Deep understanding of retrieval-augmented generation, embeddings, and vector databases (such as Pinecone, Weaviate, or FAISS)
- Familiarity with evaluation frameworks, feedback loops, and reinforcement learning techniques
- Experience building and scaling data or ML pipelines in production environments
- Curiosity about user behavior and how models can be tuned to better serve real human needs
- A thoughtful, practical approach to experimentation and iteration — you ship and learn
Bonus Points For
- Experience designing model evaluation frameworks or AI Evals
- Contributions to open-source AI infrastructure projects
- Familiarity with prompt optimization, tool calling, and agentic workflows
- Experience with multi-modal models (text, image, or speech)
- Knowledge of GCP, Firebase, or event-driven architectures
- A background in consumer or productivity products
Compensation & Benefits
- Base salary range: $150,000 – $225,000 andequity, depending on experience and expertise
- Competitive compensation package including equity
- Comprehensive medical, dental, and vision coverage
- Flexible PTO and a work culture built on trust and autonomy
- A team that values craftsmanship, collaboration, and purpose over fluff
If you’re excited by the idea of building the intelligence layer behind a product that helps people live with more clarity and calm, we’d love to meet you — even if you don’t check every box. We care about curiosity, integrity, and a shared belief in what we’re building.