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 language and/or retrieval and generation 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 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.
About Mem0
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 for our enterprise customers and our open-source community (150k+ devs and counting!). We are backed by top-tier investors through a $25M Series A & Seed.
Our Culture
Office-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.
