
2 - 10 employees
đ€ Artificial Intelligence
⥠Productivity
Artificial Intelligence âą Productivity
Memory Bridge provides a privacy-focused memory layer for AI tools, capturing context from conversations and sharing relevant information across models such as ChatGPT, Claude, and Gemini. It helps users manage memories, enrich prompts, and protect sensitive details.
đ„ 1 hour ago
Where this job comes from
Posted on Memory Bridge's careers page â, not through a job board
First seen by Remote Rocketship 1 hour ago
Still open on Memory Bridge's site. Checked 26 minutes ago.

2 - 10 employees
đ€ Artificial Intelligence
⥠Productivity
Artificial Intelligence âą Productivity
Memory Bridge provides a privacy-focused memory layer for AI tools, capturing context from conversations and sharing relevant information across models such as ChatGPT, Claude, and Gemini. It helps users manage memories, enrich prompts, and protect sensitive details.
âą Design and implement the core memory subsystem architecture, including storage tiers, retrieval pipelines, and privacy-aware filtering âą Build evaluation frameworks for memory retrieval quality, relevance scoring, and augmentation effectiveness âą Implement memory extraction and classification systems to identify, rank, and surface relevant user context from chat histories âą Research and adapt memory architectures from academic papers and open-source implementations such as MemGPT, Reflexion, and cognitive architectures âą Architect the memory update pipeline using relevance feedback, correction mechanisms, and adaptive privacy classification âą Design hybrid search strategies combining semantic embeddings, structured metadata, graph relationships, and temporal patterns âą Collaborate with the PM to define technical constraints and feature feasibility âą Own production reliability for AI features, including on-call support for prompt failures, extraction issues, and integration breakdowns âą Apply failure-mode and fallback strategies, including graceful degradation, retries, and escalation to human review âą Join as the founding ML engineer and shape production AI memory systems
âą 5+ years total experience, including at least 3 years in software engineering and 2 years building ML/NLP systems âą Hands-on experience building LLM-powered systems focused on context management, memory persistence, or personalization âą Production experience with vector databases such as Pinecone, Weaviate, Chroma, or Qdrant and hybrid search systems âą Experience shipping LLM-powered features to production âą Knowledge of prompt engineering, context window management, and API reliability patterns âą Hands-on experience with LLM orchestration frameworks including LangChain, LangGraph, Mem0, MemGPT, Letta, LlamaIndex, or Haystack âą Ability to implement hybrid search using dense vectors, sparse indices, and metadata filtering âą Strong debugging skills for RAG pipelines, prompt reliability, extraction accuracy, and function calling/MCP integrations âą Experience with agentic architectures, tool calling, MCP, and function orchestration âą Experience with privacy-preserving ML or strict data isolation requirements âą Expert Python programming âą Working knowledge of JavaScript/TypeScript for API integration and JSON schema design âą Familiarity with transformer networks and attention mechanisms âą Experience with graph databases or knowledge graphs âą Familiarity with testing LLM applications, evaluation datasets, prompt regression tests, and A/B testing âą Experience designing LLM-friendly APIs with structured outputs, streaming responses, and token optimization âą Experience with experiment tracking and model versioning âą Experience with GDPR/CCPA and data deletion, consent management, or audit trails âą Background in recommendation systems or personalization engines âą Contributions to open-source LLM/RAG projects or memory-related research âą Python, FastAPI, Git/GitHub, GitHub Actions, and JSON âą Education is not a requirement for this role
âą Remote-native work environment âą Asynchronous communication âą Sustainable performance cultureânot burnout âą Inclusive and equitable hiring process âą Equal-opportunity employment âą Opportunity to work on challenging AI problems and shape AI memory systems âą Diverse and global team/culture
Apply NowImprove your chances of getting an interview by checking your resume score before you apply.
đ April 24
Lead ML Engineer developing neural networks for lane and route networking at May Mobility. Focus on architecture, design, and validation for autonomous technology solutions.
đ Anywhere in the World
đ” $210k - $245k / year
â° Full Time
đ Senior
đ€ Machine Learning Engineer
đ January 22
Machine Learning Engineer managing and scaling multilingual data pipelines for diverse languages. Collaborating closely with researchers and engineers for robust model performance across cultural contexts.
đ January 22
ML Engineer focused on training optimization, scaling and improving large-scale model training systems. Collaborating with researchers on model architecture and capability advancement.
đ January 22
Machine Learning Engineer specializing in model distillation to create smaller, faster models for production. Engage in cutting-edge research and practical applications in a remote team.
đ January 22
Machine Learning Engineer optimizing model inference performance at scale, bridging research and production for fast, reliable ML systems.