ما به سراغ یکی از چالش‌برانگیزترین مسائل هوش مصنوعی رفته‌ایم: اینکه چطور می‌توان با کمترین خدشه به حریم خصوصی کاربران، حافظه‌ای بی‌نقص برای مدل‌های زبانی بزرگ فراهم کرد. اگر شما توسعه‌دهنده‌ی بک‌اندی هستید که عاشق طراحی سیستم‌های ماژولار، سریع، و قابل‌اعتمادید، و دلتان می‌خواهد کدی بنویسید که در دل یک محصول واقعی زندگی می‌کند، ما مشتاق آشنایی با شما هستیم. ما به‌دنبال کسی هستیم که هم از معماری داده لذت ببرد، هم بتواند با تیم ماشین لرنینگ همکاری نزدیک داشته باشد، و هم وقتی لازم است خودش تصمیم بگیرد و جلو برود.
At Memory Bridge, we're tackling one of the hardest problems in AI: giving large language models perfect memory while preserving user privacy. We're looking for an exceptional Backend Developer who understands that building a real-time memory layer for AI isn't just about connecting APIs - it's about architecting systems that can handle personal memories with low latency while maintaining bulletproof privacy guarantees. You'll design and build the infrastructure that powers our multi-tier memory system, privacy enforcement layer, and cross-platform integrations. This is a rare opportunity to join our team as the founding backend engineer, where your architectural decisions will directly shape how AI systems store, protect, and retrieve human memories. If you're a systems thinker who gets excited about distributed storage, real-time data pipelines, and privacy-first architecture, we should talk.
About You
- The ideal candidate has built production backend systems that handle sensitive user data, understanding the delicate balance between performance and privacy. You've architected APIs that serve real-time requests, designed data models that scale, and implemented security measures that protect user information by default.
- You're comfortable working across the stack when needed - from optimizing database queries to configuring deployment pipelines. You understand that in a startup, backend engineering means owning the full lifecycle of your services.
- You thrive in collaborative environments and can work effectively with ML engineers to ensure smooth integration between backend services and ML pipelines.
- You understand when to introduce complexity and when to keep things lean
- You like working in small teams where decisions move fast and ownership is shared.
- You love building resilient APIs with proper retries, circuit breakers, and fallback strategies.
Key Responsibilities
- Design and implement the core backend architecture supporting multi-tier memory storage (working, episodic, semantic), with appropriate data models and access patterns for each tier
- Build the privacy enforcement layer that ensures memory filtering happens before retrieval, implementing user-defined trust tiers and data sensitivity classifications with practical security measures
- Develop high-performance APIs that handle real-time prompt augmentation, including intelligent caching strategies and query optimization
- Architect secure multi-tenant data isolation ensuring one user's memories never leak to another, using proven patterns and appropriate encryption
- Implement robust integration pipelines for LLM providers (OpenAI, Anthropic, etc.) with proper error handling, retry logic, and graceful degradation
- Collaborate closely with the ML engineer on the hybrid retrieval system, providing backend support for vector search, keyword search, and graph queries
- Design the cross-platform synchronization system that keeps memory consistent across browser extensions and desktop applications
- Set up monitoring, logging, and alerting systems to ensure production reliability - you'll own what you build
- Work with PM to translate product requirements into technical architecture that balances features with system constraints
- Own deployment pipeline and basic infrastructure
Requirements (Must-haves)
- 4–6+ years of experience building robust backend systems
- Expert-level Python development with strong architectural pattern
- Deep understanding of asynchronous programming patterns and event-driven architectures
- Proven ability to design and operate scalable RESTful APIs with proper versioning and documentation
- Advanced PostgreSQL skills (query optimization, indexing strategies, understanding of ACID properties)
- Experience with MongoDB or similar document stores for flexible data structures
- Practical security knowledge: implementing authentication (JWT/OAuth), encryption at rest and in transit, and secure coding practices
- Experience with Redis or similar caching solutions for performance optimization
- Solid understanding of message queues for async processing
- Strong testing practices across unit, integration, and end-to-end testing
- Proficiency with Docker for containerized development and deployment
- Experience with CI/CD pipelines and automated deployment processes
- Comfort with owning production systems and debugging complex issues
- Experience with Infrastructure as Code (Terraform)
Nice-to-Have Skills
- Direct experience with LLM provider APIs and their quirks
- Background in building memory systems, caching layers, or real-time data pipelines
- Experience with observability platforms (Datadog, Prometheus/Grafana)
- Knowledge of event streaming architectures
- Experience with GitHub Actions for CI/CD automation
- Basic understanding of ML concepts to better collaborate with ML engineers
- Experience with browser extension backends
Tech Stack & Tools Core
- Python – Primary backend language for agentic services
- FastAPI – Our choice for HTTP server
- Git/GitHub – Version control and collaboration
- GitHub Actions – CI/CD automation and deployment pipelines
Databases & Caching
- PostgreSQL – Primary database for user data and relational queries
- MongoDB – Document store for flexible memory structures
- Redis – Caching layer and session management
- Vector database integration – Supporting infrastructure for ML features
Messaging & Integration
- RabbitMQ or Kafka – For async processing and event-driven architecture
- REST APIs – Primary integration pattern
Infrastructure & DevOps
- Docker & Docker Compose – Containerization and local development
- Basic cloud deployment – Scripted deployments, not over-engineered
- Monitoring basics – Logging, metrics, and alerting (specific tools flexible)
Security & Integration
- Authentication – JWT and OAuth 2.0 basics
- HTTPS/TLS – Standard encryption in transit
- Environment-based secrets management – Not necessarily a complex vault system
- Rate limiting – Basic protection against abuse
•
How To Apply At Memory Bridge, we believe that diverse perspectives and experiences make us better, which is why we have a non-standard application process designed to promote inclusion and equity. We're looking for the best fit for each of our roles, regardless of the type of companies in your background, so we encourage you to apply even if your skills and experiences don't exactly match the job description. All we ask is that you answer a few in-depth questions in our application that would typically be asked at the start of an interview process. This helps speed things up by letting us get to know you and your skillset a bit better right out of the gate. Please be sure to answer each question; the updated resume is essential. Education is not a requirement for our roles; however, if you receive an offer, you will need to include your most recent educational experience as part of our background check process. Memory Bridge is an equal-opportunity employer and we're excited to work with talented and empathetic people of all identities. Memory Bridge does not discriminate based on someone's identity in any aspect of hiring or employment, as required by law and in line with our commitment to Diversity, Inclusion, Belonging, and Equity. Our code of conduct provides a beacon for the kind of company we strive to be, and we celebrate our differences because those differences are what allow us to make a product that serves a global user base. Memory Bridge will consider all qualified applicants, including those with criminal histories, consistent with applicable laws. The anticipated application window is 30 days from the date the job is posted, unless the number of applicants requires it to close sooner or later, or if the position is filled. How We Work We are a remote-native company, intentionally designed for deep work and focused execution. We hire the best minds, wherever they are, and empower them to solve some of the hardest problems in AI. Our culture thrives on asynchronous communication, radical transparency, and a commitment to sustainable performance - not burnout. If you're obsessed with building the infrastructure layer that will power the future of personalized AI and want to solve hard problems at the intersection of performance, privacy, and scale, we want to hear from you.