Location:
Anywhere, Worldwide
About the Company & Product
Our client is a well-funded AI startup building a next-generation multi-agent AI orchestrator for the wealth management industry. Their platform - already in production and actively used by clients - analyzes behavioral patterns, communication preferences, and client data to help financial advisors deliver a more personalized, high-impact service.
The team is small and highly focused. The technology works, early customers are seeing strong results, and now the company is building out its engineering function to scale. This is a rare early-stage opportunity with real ownership and meaningful equity.
The Role
Our client is looking for an AI/Backend Engineer to own and evolve their LLM orchestration pipeline. The successful candidate will work directly with the CTO to transform a working prototype into a scalable, enterprise-ready platform.
This is a high-impact, high-autonomy role offered on a B2B contract basis. The engineer joining at this stage will shape technical decisions that define the product for years to come.
Key Responsibilities
AI Pipeline Ownership
- Design and optimize a multi-agent orchestration system
- Implement parallelization and streaming to reduce response latency
- Build robust prompt management with versioning and A/B testing capabilities
RAG System Development
- Design retrieval-augmented generation for accurate, contextual responses
- Work with vector databases, embeddings, and relevance scoring
- Optimize for both speed and accuracy at scale
Production API Development
- Build developer-friendly APIs connecting AI capabilities to the frontend
- Design for future integrations with CRMs and financial advisor tools
- Implement proper authentication, rate limiting, and documentation
Technical Foundation
- Establish code review practices and testing standards
- Document architecture decisions for future team members
- Contribute to technical patents and IP development
Candidate Profile
Must Have
- 4+ years of 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
- Production 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 familiarity
- FinTech or regulated industry background
How You Work
- Self-directed and comfortable with ambiguity
- Strong written communication - we are an async-first culture
- Pragmatic problem-solver who ships iteratively
- Collaborative mindset with an ego-free approach to feedback
Important to Know
- This is not a pure ML/research role - the focus is on applying LLMs, not training them
- Not a management role - near-term focus is individual contribution
- Close collaboration with the CTO is expected on all architectural decisions
- Startup pace applies - flexible hours, but high ownership and engagement are expected
Compensation & Benefits
- Equity: Meaningful early-stage grant with 4-year vesting
- Equipment: Professional laptop provided + remote work stipend after 6 months
- Time Off: Flexible PTO - minimum 15 days encouraged
- Learning: $1,000 annual professional development budget
- Schedule: Flexible hours with 4-5 hours daily overlap across European timezones
Interview Process
- TA Screen - 45 min conversation to discuss your background and the role
- Technical Interview - 60 min deep-dive with the CTO on architecture and hands-on experience
- Take-Home Assessment - practical task reviewed collaboratively (4-6 hours)
- Values & Fit - 45 min conversation to explore culture and working style alignment
Total timeline: 2-3 weeks
How to Apply
If this opportunity looks like the right fit, please send your CV along with a brief note on your relevant experience and why this role interests you. Links to GitHub, portfolio, or any products you have contributed to are very welcome.
*Al tools are used to support the recruitment process for this role. All candidate evaluations are made by our recruitment team.
