Research Engineer - Agent Memory

Mem0 is building the memory layer for AI agents, enabling long-term memory for AI interactions. As a Research Engineer, you will fine-tune models for memory extraction, updates, and consolidation, turning research ideas into production features within weeks. You'll own the evaluation layer and ship models at SOTA latency and reliability, working in-office in San Francisco.

• Train models: Memory extraction, updates, consolidation/forgetting, and conflict resolution, iterating fast on real data and real outcomes.
• Live at the research frontier: Turn paper ideas into working prototypes in days, benchmark them honestly against baselines, and productionize the ones that actually win.
• Build the evaluation layer: Automated relevance/accuracy/consistency metrics, gold sets, online A/B and interleaving tests, and dashboards people actually check.
• Get close to the problem: Uncover what's actually breaking for customers, turn it into a testable hypothesis, and validate it through real field trials.
• Ship it for real: Design APIs and data contracts, plan safe rollouts, and hit SOTA latency, reliability, and cost, with Engineering, not over the wall from them.

• Experience in RAG or information retrieval (retrieval, ranking, query understanding) for real products.
• Model training/fine-tuning experience (LLMs/encoders) with a strong footing in experimental design and iteration.