AI Backend Engineer

About Prospera AI We're building Sophie, a multi-agent AI orchestrator that helps wealth management advisors deliver more personalized, effective service to their clients. Our platform analyzes behavioral patterns, communication preferences, and emotional states to transform how advisors understand and serve their clients. We're a small, well-funded team at an exciting inflection point — our technology works, customers love the product, and now we're building the engineering team to scale. The Role We're looking for an AI/Backend Engineer to own and evolve our LLM orchestration pipeline. You'll be the first dedicated engineering hire, working directly with our CTO to transform Sophie from a working prototype into a scalable, enterprise-ready platform. This is a high-impact, high-autonomy role. You'll shape technical decisions that define the product for years to come. What You'll Do Own the AI Pipeline Design and optimize our multi-agent orchestration systemImplement parallelization and streaming to dramatically reduce response latencyBuild robust prompt management with versioning and A/B testing capabilities Build RAG Systems Design retrieval-augmented generation for accurate, contextual responsesWork with vector databases, embeddings, and relevance scoringOptimize for both speed and accuracy at scale Develop Production APIs Build developer-friendly APIs connecting our AI capabilities to the frontendDesign for future integrations with CRMs and advisor toolsImplement proper authentication, rate limiting, and documentation Shape the Foundation Establish code review practices and testing standardsDocument architecture decisions for future team membersContribute to technical patents and IP development What We're Looking For Must Have 4+ years production Python experience (async patterns, type hints)Hands-on experience with LLM APIs (OpenAI, Anthropic, or similar)Strong understanding of prompt engineering and multi-step LLM workflowsProduction API development experience (FastAPI or similar)Strong SQL and PostgreSQL skills Great to Have Experience with RAG systems and vector databases (Pinecone, Weaviate, pgvector)Streaming/real-time implementation experience (SSE, WebSockets)TypeScript/JavaScript familiarityFinTech or regulated industry background How You Work Self-directed and comfortable with ambiguityStrong written communication (async-first culture)Pragmatic problem-solver who ships iterativelyCollaborative mindset with ego-free approach to feedback What This Role Is Not Not a pure ML/research role — you'll apply LLMs, not train themNot a management role — near-term focus is individual contributionNot fully autonomous — you'll collaborate closely with the CTO on architectureNot 9-to-5 — startup intensity applies, though we respect work-life balance Compensation & Benefits BaseCompetitive — Based on experience and location EquityMeaningful early-stage grant with 4-year vesting EquipmentProfessional laptop provided + remote work stipend after 6 months Time OffFlexible PTO with minimum 15 days encouraged LearningAnnual professional development budget ScheduleFlexible hours with 3–4 hours daily overlap Americas timezones Interview Process 1 Resume Review— 1–2 day turnaround 2 Technical Screen— 60 min video conversation with CTO 3 Take-Home Assessment— 4–6 hours (to be reviewed) 4 Assessment Deep Dive— 90 min collaborative review 5 Values & Fit— 45 min conversation 6 References & Offer Total timeline: 2–3 weeks