AI Backend Engineer

About the Company

Prospera AI is building Sophie, a multi-agent AI orchestrator designed to help wealth management advisors deliver more personalized and effective service. We are a small, well-funded team at an exciting inflection point, transforming a working prototype into a scalable, enterprise-ready platform.

Responsibilities

• Design and optimize the multi-agent orchestration system
• Implement parallelization and streaming to reduce response latency
• Build robust prompt management with versioning and A/B testing
• Design retrieval-augmented generation (RAG) systems using vector databases and embeddings
• Develop production-ready APIs connecting AI capabilities to the frontend
• Establish code review practices, testing standards, and architectural documentation

Requirements

• 4+ years of production Python experience (async patterns, type hints)
• Hands-on experience with LLM APIs (OpenAI, Anthropic, etc.)
• Strong understanding of prompt engineering and multi-step LLM workflows
• Experience with production API development (FastAPI or similar)
• Strong SQL and PostgreSQL skills

Preferred Qualifications

• Experience with RAG systems and vector databases (Pinecone, Weaviate, pgvector)
• Experience with streaming/real-time implementations (SSE, WebSockets)
• Familiarity with TypeScript/JavaScript
• Background in FinTech or regulated industries

Benefits

• Meaningful early-stage equity grant with 4-year vesting
• Professional laptop and remote work stipend
• Flexible PTO (minimum 15 days encouraged)
• $1,000 annual professional development budget
• Flexible hours with 3-4 hours daily overlap in Americas timezones