Backend Engineer

About Mem0

Mem0 is developing an advanced memory layer for AI agents that enables them to remember conversations, learn from interactions, and build meaningful context over time, transcending traditional chatbot capabilities. The platform currently supports millions of AI interactions for enterprise clients and a rapidly expanding open-source community of more than 160,000 developers. Supported by $24M in combined Series A and Seed funding from leading investors, Mem0 aims to create foundational systems influencing future AI products.

Role Overview

This position is responsible for owning and evolving the backend platform supporting Mem0's AI memory layer. Responsibilities include designing and implementing clean RESTful APIs, modeling data using both relational databases and graph stores, and maintaining production services. Collaborating closely with the frontend and research teams, you'll troubleshoot customer issues through root-cause analysis, deploy fixes, and strengthen system reliability.

Key Responsibilities

• Architect and deliver robust REST APIs with defined contracts, authentication, versioning, rate limiting, migrations, and documentation.
• Design and optimize data schemas leveraging relational databases such as Postgres and graph databases like Neo4j, ensuring data integrity and efficient performance.
• Investigate and resolve customer-reported issues end-to-end using logs, metrics, and tracing tools; implement preventive measures to avoid recurrence.
• Enhance system performance through SQL query optimization using EXPLAIN and ANALYZE, indexing, partitioning, pagination, and caching mechanisms including Redis.
• Develop backend services in Python, utilizing asynchronous programming where advantageous, with frameworks such as FastAPI, Django/DRF, or Flask, and including background job processing.
• Manage cloud infrastructure operations deploying containerized applications with Docker, Kubernetes (EKS), and AWS services like EC2, RDS/Aurora, S3, and IAM.
• Implement comprehensive system observability with custom metrics, structured logging, distributed tracing, and configure SLOs and alerts via tools like CloudWatch, Prometheus, and OpenTelemetry.
• Collaborate cross-functionally to scope API features and deliver reliable production-ready software.

Qualifications and Experience

• Minimum 5 years of experience designing and deploying backend systems and REST APIs in production environments.
• Strong proficiency in Python, including asynchronous programming and significant experience with major web frameworks such as FastAPI, Django/DRF, or Flask.
• Advanced skills in data modeling and SQL with practical expertise in query performance tuning and debugging in Postgres or MySQL.
• Experience working with graph databases like Neo4j or Amazon Neptune, understanding their data modeling considerations.
• Comfortable operating cloud-based backend services using Docker containers and Kubernetes orchestration on AWS.
• Proven ability to perform root-cause analysis, manage incidents effectively, and implement preventive solutions.
• Excellent communication capabilities and collaborative mindset, working effectively with frontend developers, research teams, and clients.

Additional Preferred Skills

• Experience with GraphQL or gRPC APIs; familiarity with event-driven architectures using SNS, SQS, or Kafka, and background processing with Celery or RQ.
• Knowledge of caching strategies, rate limiting, multi-tenancy architectures, and feature flag implementations.
• Understanding of security and privacy best practices including handling of personally identifiable information (PII) and secret management.
• Expertise in observability technologies such as OpenTelemetry and SLO-based alerting systems.
• Background in search, retrieval, or memory system development.
• Hands-on experience with on-call responsibilities and conducting blameless postmortems.
• Prior involvement with early-stage startups, Series A funding rounds, Y Combinator programs, or founding engineer roles.

Company Culture

• We prioritize fast development coupled with craftsmanship; aiming for long-term scalable, reliable, and elegant solutions.
• We promote extreme ownership; every team member acts as an owner, taking initiative to address problems or opportunities.
• High trust and high standards define our environment, where ideas are openly challenged and celebrated with respect.
• We make decisions grounded in data and outcomes rather than ego, valuing the best solution regardless of the source.