AI Full Stack Engineer
$150k - $250k • San Francisco Bay Area • FullTime
Posted 6d ago
Job Location
San Francisco Bay Area
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Engineer
About the job
Mem0 is building the memory layer for AI agents, enabling them to remember conversations, learn from interactions, and build context over time. We are a Y Combinator-backed company with significant funding, powering millions of AI interactions for enterprise customers and an open-source community. This full-time, onsite role in San Francisco, CA, offers a unique opportunity to own the AI product surface of the Mem0 Platform. You will be responsible for the end-to-end frontend development, setting the visual and interaction standards for our dashboard, playground, and documentation. Working directly with the CTO, research, and customers, you will translate complex memory problems into intuitive user interfaces, shipping AI products to real users.
Responsibilities
- Design and build the Mem0 dashboard, playground, and developer surfaces using Next.js and React, including setting design direction and managing the component system.
- Ship AI features end-to-end, including designing APIs, building retrieval and memory pipelines, owning data models, and deploying to production.
- Build and deploy LLM-powered features in production, working with embeddings, vector search, RAG, function calling, and agent orchestration.
- Develop evaluation metrics, golden datasets, and regression suites to ensure the quality and evidence-based deployment of model and prompt changes.
- Optimize the stack for scale and speed, focusing on retrieval latency, caching, database queries, bundle size, and inference costs.
- Write tests, maintain strong typing and linting standards, conduct code reviews, and ensure codebase cleanliness.
- Collaborate with Research to integrate new memory capabilities and engage directly with customers to refine product development.
- Implement observability for application and model behavior, monitor production systems, troubleshoot issues, and improve reliability.
- Make informed technical and product tradeoffs, prioritize effectively, and iterate based on user feedback and data.
- Support teammates, quickly adopt new technologies, and contribute to overall delivery goals.
Requirements
- 5+ years of experience building and shipping production-grade full-stack applications at scale.
- Deep expertise in Next.js, React, and TypeScript, with a proven track record of owning product look and feel in production.
- Strong design sense and the ability to create polished, accessible interfaces independently.
- Hands-on experience shipping AI-native products to real users using LLMs, RAG, embeddings, or vector databases.
- Strong proficiency in Python and modern web application architecture.
- Experience with REST APIs, PostgreSQL, Redis, background job systems, and modern backend frameworks.
- Practical experience with prompt engineering, model evaluation, and debugging non-deterministic systems.
- Demonstrated ability to own features end-to-end, from technical design through deployment and iteration.
- Strong engineering fundamentals including testing, CI/CD, type safety, maintainability, and code quality.
- Experience operating production systems with logging, metrics, tracing, and monitoring, meeting low-latency requirements.
- Excellent communication skills and comfort interacting directly with customers and leadership.
- Bachelor's or Master's in Computer Science or a related technical field, or equivalent experience.