About Prospera AIWe’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 RoleWe’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 DoOwn the AI PipelineDesign and optimize our multi-agent orchestration systemImplement parallelization and streaming to dramatically reduce response latencyBuild robust prompt management with versioning and A/B testing capabilitiesBuild RAG SystemsDesign retrieval-augmented generation for accurate, contextual responsesWork with vector databases, embeddings, and relevance scoringOptimize for both speed and accuracy at scaleDevelop Production APIsBuild developer-friendly APIs connecting our AI capabilities to the frontendDesign for future integrations with CRMs and advisor toolsImplement proper authentication, rate limiting, and documentationShape the FoundationEstablish code review practices and testing standardsDocument architecture decisions for future team membersContribute to technical patents and IP developmentWhat We’re Looking ForMust Have4+ 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 skillsGreat to HaveExperience with RAG systems and vector databases (Pinecone, Weaviate, pgvector)Streaming/real-time implementation experience (SSE, WebSockets)TypeScript/JavaScript familiarityFinTech or regulated industry backgroundHow You WorkStrong UX intuition—you notice when flows have one too many clicksPragmatic perfectionism—you know when to polish and when to shipClear communicator who can explain technical constraints in business termsCollaborative mindset—frontend doesn’t exist in isolationHow You WorkSelf-directed and comfortable with ambiguityStrong written communication (async-first culture)Pragmatic problem-solver who ships iterativelyCollaborative mindset with ego-free approach to feedbackWhat This Role Is NotWe want to be upfront about expectations: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 balanceCompensation & BenefitsEquity: Meaningful early-stage grant with 4-year vestingEquipment: Professional Laptop ready to work with AI provided + stipend for remote work when 6 month mark is metTime Off: Flexible PTO with a minimum 15 days encouragedLearning: $1,000 annual professional development budgetSchedule: Flexible hours with 3-4 hours daily overlap (Americas timezones)The Interview ProcessSilver.dev Recruiter ScreenSilver.dev System Design ScreenTechnical Screen & System Design Interview with Tech Lead + CTOAssessment Deep-Dive with Senior Engineer + CTOCulture Fit Check with CEO