We're building the memory layer for AI agents. Think long-term memory that enables AI to remember conversations, learn from interactions, and build context over time. We're already powering millions of AI interactions. We are backed by top-tier investors and are well capitalized.
The hard problem: maintaining sub-100ms p99 latency while scaling exponentially. Most companies throw hardware at this. We're looking for someone who gets excited about making systems fundamentally faster.
Our CultureOffice-first collaboration - We're an in-person team in San Francisco. Hallway chats, impromptu whiteboard sessions, and shared meals spark ideas that remote calls can't.
Velocity with craftsmanship - We build for the long term, not just shipping features. We move fast but never sacrifice reliability or thoughtful design - every system needs to be fast, reliable, and elegant.
Extreme ownership - Everyone at Mem0 is a builder-owner. If you spot a problem or opportunity, you have the agency to fix it. Titles are light; impact is heavy.
High bar, high trust - We hire for talent and potential, then give people room to run. Code is reviewed, ideas are challenged, and wins are celebrated—always with respect and curiosity.
Data-driven, not ego-driven – The best solution wins, whether it comes from a founder or an engineer who joined yesterday. We let results and metrics guide our decisions.
You'll own the infrastructure that makes personalized AI possible at scale. This is deep technical work - profiling systems, rewriting queries, building monitoring, and ensuring our infrastructure can handle exponential growth. You'll work directly with our founding team with significant autonomy to solve hard performance problems. When you ship code, millions of AI interactions depend on it working flawlessly.
What You'll Do:Optimize retrieval performance: Profile and rewrite database queries across our multi-store architecture to achieve < 100ms p99 latency
Scale infrastructure systems: Design and implement auto-scaling, connection pooling, and distributed caching to handle exponential growth
Build end-to-end monitoring & alerting: Instrument the entire stack with detailed observability to maintain 99.99% uptime
Design disaster-recoverable, multi-AZ systems: Implement robust failover mechanisms and geographic redundancy for mission-critical memory operations
Debug production issues: On-call rotation to investigate and resolve infrastructure problems in real-time
Implement reliability improvements: Build circuit breakers, retry logic, graceful degradation for mission-critical memory operations
Optimize data pipelines: Improve memory ingestion, processing, and retrieval workflows for efficiency and accuracy
You may be a good fit if you:
5+ years hands-on backend/infrastructure engineering experience
Deep database expertise: Production experience optimizing PostgreSQL, Redis, or graph databases (Neo4j preferred)
Performance tuning mastery: Proven track record of 10x performance improvements (link to talk or PR a plus)
Production scaling experience: Built systems handling millions of requests/day with strict latency requirements
Infrastructure automation: Hands-on experience with Kubernetes, Terraform, CI/CD pipelines
Monitoring & observability: Experience with APM tools, metrics, logging, alerting systems
Startup mentality: Thrives in ambiguity; defaults to action
Strong candidates may also have:
Built or optimized vector databases, embedding systems, or ML infrastructure
Experience with sub-100ms latency requirements (trading firms, gaming, real-time systems)
Background at infrastructure companies (Redis, MongoDB, Databricks, etc.)
Open source contributions to performance-critical projects
Experience debugging with perf, flamegraphs, or distributed tracing
Relocation and immigration support offered. We welcome engineers from non-traditional backgrounds and under-represented groups - if the mission excites you, please apply
What we're building matters. Every AI interaction that remembers context, every agent that learns from previous conversations, every personalized AI experience - it runs through infrastructure like ours.
Ready to make AI memory work at internet scale?
