Research Engineer - Agent Memory

Mem0
San Francisco
Workplace: OnsiteFull timeUSD 175,000 - 250,000 annuallyFunction: Research & Scientific (R&D)Experience: 3+ yearsSkills: ["Communication","Stakeholder management"]

Build the memory layer that helps AI agents retain long-term context—deciding what to remember, forget, and learn. Own memory model fine-tuning and iteration from paper ideas to production A/B tests within weeks. Create an evaluation layer with offline metrics and online experiments, uncover customer failure modes, and ship low-latency, reliable, cost-aware APIs and data contracts in an in-office team in San Francisco.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Mem0
Mem0
1 month ago

Research Engineer - Agent Memory

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 16 hours agoStatus: Live

Job Summary

Build the memory layer that helps AI agents retain long-term context—deciding what to remember, forget, and learn. Own memory model fine-tuning and iteration from paper ideas to production A/B tests within weeks. Create an evaluation layer with offline metrics and online experiments, uncover customer failure modes, and ship low-latency, reliable, cost-aware APIs and data contracts in an in-office team in San Francisco.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Train and improve memory extraction, updates, consolidation/forgetting, and conflict resolution using real data and outcomes.
  • •Turn paper ideas into prototypes quickly, benchmark against baselines, and productionize the approaches that win.
  • •Build the evaluation layer with relevance/accuracy/consistency metrics, gold sets, and online A/B or interleaving tests with dashboards.
  • •Identify what breaks for customers, form testable hypotheses, and validate them through field trials.
  • •Design APIs and data contracts, plan safe rollouts, and deliver SOTA latency, reliability, and cost with Engineering.

Pay and Benefits

Salary: USD 175,000 - 250,000 annually
Perks:Health InsuranceDentalVisionEquityPaid LeaveMeal Allowance401k

Key Requirements

  • •Experience in RAG or information retrieval (retrieval, ranking, query understanding) for real products.
  • •Model training/fine-tuning experience with LLMs/encoders, plus strong experimental design and iteration.
  • •Strong Python with deep experience in PyTorch and familiarity with vLLM and modern serving frameworks.
  • •Experience building evaluation for language and/or retrieval + generation tasks (gold sets, offline metrics, online tests).
  • •Ability to orchestrate production data pipelines with low-latency SLAs (batch + streaming).
Experience:3+ years
Skills:CommunicationStakeholder management
Tech Stack:PythonPyTorchVLLMRAG

Eligibility

Nationality:US National

Company Brief

Mem0
Mem0 develops AI-driven memory and knowledge management solutions to help organizations capture, store, and retrieve contextual information, augment workflows, improve decision-making, and enable more efficient interactions with large language models and enterprise data.
Industry: Data Infrastructure
Website