About the Role
The role involves building and optimizing backend systems that power AI features, particularly retrieval-augmented generation pipelines, ensuring scalability, reliability, and low-latency performance.
Responsibilities
- Design and implement scalable backend services for AI applications
- Develop and maintain retrieval-augmented generation (RAG) pipelines
- Optimize data flow and storage for low-latency query responses
- Collaborate with machine learning engineers to integrate models into production
- Ensure API reliability and performance under high load
- Write clean, maintainable, and well-tested code
- Troubleshoot and resolve production issues quickly
- Participate in system architecture decisions
- Improve observability and monitoring across services
- Support deployment automation and CI/CD workflows
- Evaluate and integrate new technologies to improve system capabilities
- Maintain data consistency across distributed systems
- Contribute to security best practices in backend infrastructure
- Work closely with frontend teams to define efficient interfaces
- Refactor legacy components for better performance and scalability
- Help define technical standards and coding practices
- Participate in code reviews and knowledge sharing
- Ensure compliance with data privacy requirements
- Support on-call rotations for critical systems
- Document system designs and operational procedures
Nice to Have
- Experience with large language model deployment
- Contributions to open-source AI projects
- Prior work in early-stage startups
- Knowledge of natural language processing
- Familiarity with transformer-based architectures
- Experience with real-time data pipelines
- Background in search or recommendation systems
- Published research or patents in AI/ML
Compensation
Competitive salary with equity and benefits
Work Arrangement
Remote-first with optional hubs
Team
Small, agile team focused on rapid iteration and technical excellence
Tech Stack
- Primary languages: Python, Go
- Infrastructure: AWS, Kubernetes, Docker
- Databases: PostgreSQL, Redis, Pinecone
- AI tools: LangChain, Hugging Face, OpenAI APIs
- Monitoring: Prometheus, Grafana, ELK stack
Culture & Values
- We prioritize technical depth over bureaucracy
- Autonomy is expected and trusted
- Decisions are data-driven and user-focused
- Transparency is core to how we operate
- We value sustainable pace and deep work
Available for qualified candidates
