Senior RAG Engineer - LangChain/Production AI Systems

About us

Wallester is a cutting-edge financial technology company that specializes in providing innovative solutions for businesses seeking to modernize their payment systems. By offering white-label card issuance platforms, seamless integration with existing infrastructure, and comprehensive support for both digital and physical cards, Wallester empowers companies to enhance their financial services and customer experience. Recognized as a leader in the FinTech space, Wallester has earned a reputation for its state-of-the-art technology, security, and scalability. Whether you are a startup or an established enterprise, Wallester delivers flexible, reliable solutions tailored to meet the evolving needs of the digital economy.

About the position

We're seeking an exceptional engineer specialized in RAG (Retrieval-Augmented Generation) systems to build Wallester's intelligent knowledge base. You'll be responsible for the architecture, development, and deployment of a RAG system capable of ingesting housands of documents (Drive, emails, history) and providing perfect institutional memory accessible in natural language. Progressive deployment over 9 months: General knowledge base → Department integrations (Sales, Finance, Support) → Advanced features and scaling.

We're looking for a true expert capable of designing and implementing complex RAG architectures with LangChain/LangGraph and orchestrating workflows with n8n.

Responsibilities

General Knowledge Base

- Design complete RAG architecture with LangChain

- Implement Google Drive ingestion pipeline (5000+ documents)

- Build 3-way hybrid search (semantic + BM25 + pattern matching)

- Deploy Supabase with pgvector optimization

- Create LangGraph workflows for orchestration

Department Integrations

- Connect Pipedrive (Sales), Admin Panel (Finance), Support systems

- Develop autonomous agents per department with LangGraph

- Build n8n workflows for business logic

- Implement conversation memory and query routing

Production & Scaling

- Optimize for 1000+ queries/day with <1s latency

- Implement intelligent caching and error handling

- Set up RAG evaluation metrics (precision, recall, faithfulness)

- Monitor with LangSmith/LangFuse

Requirements

We're looking for an expert who:

- Truly masters LangChain/LangGraph in production

- Has built production RAG systems (not just POCs)

- Understands trade-offs (latency, quality, cost, chunking)

- Knows the LangChain ecosystem (LangSmith, LangFuse, integrations)

Experience:

- 3-5 years minimum in software development with production AI/ML projects

- Python expert with complex production projects

- LangChain/LangGraph: Confirmed production experience (required)

- n8n: Production workflow experience with complex pipelines (required)

- RAG/LLM portfolio: Deployed systems, GitHub, technical articles

- Bonus: TypeScript, Redis, advanced n8n scaling (workers, queues)

Company offers:

• Competitive salary
• Career opportunities
• Supportive and caring Leadership
• A chance to work as part of a highly motivated and talented team
• Team building and Company Events