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 system • Implement parallelization and streaming to dramatically reduce response latency • Build robust prompt management with versioning and A/B testing capabilities Build RAG Systems • Design retrieval-augmented generation for accurate, contextual responses • Work with vector databases, embeddings, and relevance scoring • Optimize for both speed and accuracy at scale Develop Production APIs • Build developer-friendly APIs connecting our AI capabilities to the frontend • Design for future integrations with CRMs and advisor tools • Implement proper authentication, rate limiting, and documentation Shape the Foundation • Establish code review practices and testing standards • Contribute 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 workflows • Strong SQL and PostgreSQL skills Great to Have • Experience with RAG systems and vector databases (Pinecone, Weaviate, pgvector) • FinTech or regulated industry background How You Work • Self-directed and comfortable with ambiguity • Strong written communication (async-first culture) • Pragmatic problem-solver who ships iteratively • Collaborative mindset with ego-free approach to feedback What This Role Is Not • Not a pure ML/research role — you\'ll apply LLMs, not train them • Not a management role — near-term focus is individual contribution • Not fully autonomous — you\'ll collaborate closely with the CTO on architecture • Not 9-to-5 — startup intensity applies, though we respect work-life balance Base Competitive — Based on experience and location Equity Meaningful early-stage grant with 4-year vesting Equipment Professional laptop provided + remote work stipend after 6 months Time Off Flexible PTO with minimum 15 days encouraged Schedule Flexible hours with 3–4 hours daily overlap Americas timezones Interview Process Resume Review — 1–2 day turnaround Technical Screen — 60 min video conversation with CTO Take-Home Assessment — 4–6 hours (to be reviewed) Values & Fit — 45 min conversation References & Offer Total timeline: 2–3 weeks Apply for this role Fill out the form below. We\'ll review your application and get back to you within a few days. #J-18808-Ljbffr