Research Engineer - Agent Memory

Role Summary: Own the end-to-end lifecycle of memory features—from research to production. You’ll fine-tune models for extraction, updates, consolidation/forgetting, and conflict resolution; turn customer pain points into research hypotheses; implement and benchmark ideas from papers; and ship with Engineering to SOTA latency, reliability, and cost. You’ll also build evaluation at scale (offline metrics + online A/Bs) and close the loop with real-world feedback to continuously improve quality. What You'll Do: - Fine-tune and train models for memory extraction, updates, consolidation/forgetting, and conflict resolution; iterate based on data and outcomes. - Read, reproduce, and implement research: quickly prototype paper ideas, benchmark against baselines, and productionize what wins. - Build evaluation at scale: automated relevance/accuracy/consistency metrics, gold sets, online A/B & interleaving, and clear dashboards. - Work closely with customers to uncover pain points, turn them into research hypotheses, and validate solutions through field trials. - Partner with Engineering to ship: design APIs and data contracts, plan safe rollouts, and maintain SOTA latency, reliability, and cost at scale. Minimum Qualifications - 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. - Strong Python; deep experience with PyTorch and familiarity with vLLM and modern serving frameworks. - Built evaluation for complex vision-and-language tasks (gold sets, offline metrics, online tests). - Able to orchestrate data pipelines to run these models in production with low-latency SLAs (batch + streaming). - Clear, concise communication with stakeholders (engineering, product, GTM, and customers). Nice to Have: - Publications at venues like CVPR, NeurIPS, ICML, ACL, etc. - Experience with privacy-preserving ML (redaction, differential privacy, data governance). - Deep familiarity with memory/retrieval literature or prior work on memory systems. - Expertise with embeddings, vector-DB internals, deduplication, and contradiction detection. OUR CULTURE - Office-first collaboration We're an in-person team based in San Francisco. Hallway conversations, whiteboard sessions, and spontaneous collaboration help us move faster and build better products than remote meetings alone. - Velocity with craftsmanship We move quickly without sacrificing engineering excellence. Every system we build should be fast, reliable, scalable, and thoughtfully designed. - Extreme ownership Everyone at Mem0 is a builder-owner. If you see a problem or opportunity, you're empowered to solve it. Titles matter less than impact. - High bar, high trust We hire exceptional people, give them autonomy, and hold ourselves to a high engineering standard. We challenge ideas, review code thoughtfully, and celebrate wins together. - Data-driven, not ego-driven The best ideas win regardless of where they come from. We rely on data, customer feedback, and thoughtful experimentation to guide decisions. BENEFITS & PERKS - Health, dental & vision coverage - Comprehensive plans, fully covered for you (and subsidized for dependents) - Lunch & dinner, on us - Daily meals catered in-office, because good food fuels good work - Flexible PTO - Take the time you need to recharge, no rigid accrual counting - Equity in an early-stage company - Real ownership in what you're building, not just a paycheck - Regular team happy hours & events - Built into the culture, not an afterthought - Top-tier equipment - The laptop and setup you need to do your best work