Research Engineer - Agent Memory

Mem0; San Francisco (CA); On-site; USD 175,000 - 250,000; Full time

Job summary

Mem0 in San Francisco, CA is seeking an ML engineer to 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, translating customer pain points into research hypotheses and benchmarking ideas from papers.

You’ll collaborate with Engineering to ship with SOTA latency, reliability, and cost, and build evaluation at scale with offline metrics and online A/B tests to continually

Qualifications

• Experience in RAG or information retrieval for real products.
• Model training/fine-tuning experience (LLMs/encoders) with experimental design.
• Strong Python; PyTorch and familiarity with vLLM and serving frameworks.
• Built evaluation for complex vision-and-language tasks (gold sets, offline metrics, online tests).
• 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).

Responsibilities

• 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: prototype 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.

Skills

RAG / information retrieval

Model fine-tuning

Python & PyTorch

Evaluation / metrics

Data pipelines

Stakeholder communication

Tools

vLLM

Vector databases

Job description

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

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.
  

Compensation Range: $175K - $250K