Qualifications

• 5+ years experience developing production backend systems with Python and async I/O expertise.
• Hands-on experience designing and scaling REST or async APIs with a focus on clean service architecture.
• Practical experience integrating LLM APIs such as OpenAI or Gemini into backend systems.
• Experience with vector databases and Retrieval-Augmented Generation (RAG) architectures.
• Strong skills in relational database management including schema design and query optimization.
• Familiarity with AI-augmented delivery practices throughout the software lifecycle.
• End-to-end ownership of CI/CD processes from build through deployment.

Responsibilities

• Design and scale async REST/WebSocket APIs in Python using advanced coding practices.
• Implement multi-agent workflows to facilitate work routing among specialized LLM agents.
• Integrate multiple LLM providers via a provider-agnostic layer for improved metrics.
• Build and maintain RAG pipelines connected to vector storage solutions.
• Design and evolve databases that support traditional and AI-driven application features.
• Instrument services to track performance metrics effectively under production load.
• Take ownership of the entire delivery lifecycle while establishing coding guardrails for AI integration.

Benefits

• Work-life balance in a culture that respects personal time.
• A culture of belonging with over 20 affinity groups for employee connection.
• Comprehensive health benefits including HSA, dental, and vision coverage.
• Retirement support through a matching 401K program.
• Generous paid time off alongside additional benefits like Pet Insurance.
• Opportunities for mentorship and career growth within the organization.