AI/Backend Engineer – LLM Orchestration

About the role

Prospera AI is building Sophie, a multi‑agent AI orchestrator for wealth‑management advisors. We are looking for an AI/Backend Engineer to own and evolve the LLM orchestration pipeline, turning a prototype into a scalable, enterprise‑ready platform.

Key responsibilities

• Design, implement and optimise a multi‑agent orchestration system with parallelisation and streaming.
• Build robust prompt‑management tools with versioning and A/B testing.
• Develop retrieval‑augmented generation (RAG) pipelines using vector databases and embeddings.
• Create production‑grade APIs (FastAPI) for frontend integration, including authentication, rate limiting and documentation.
• Establish code‑review, testing standards and architectural documentation.
• Contribute to technical patents and intellectual property.

Required profile

• 4+ years of production Python development, comfortable with async patterns and type hints.
• Hands‑on experience with LLM APIs (e.g., OpenAI, Anthropic).
• Strong understanding of prompt engineering and multi‑step LLM workflows.
• Experience building production APIs (FastAPI or similar) and working with PostgreSQL.

Required skills

• Python
• Async programming
• LLM APIs (OpenAI, Anthropic)
• Prompt engineering
• FastAPI
• SQL / PostgreSQL
• RAG systems
• Vector databases (Pinecone, Weaviate, pgvector)
• Streaming technologies (SSE, WebSockets)
• TypeScript / JavaScript (familiarity)

What we offer

• Competitive base salary based on experience and location.
• Early‑stage equity grant with a four‑year vesting schedule.
• Professional laptop and remote‑work stipend after six months.
• Flexible PTO and a supportive, async‑first culture.