Role overview
We are an equal opportunity employer. We value diversity and are committed to an inclusive environment for all employees. If you are excited about the role but don't meet 100% of the requirements, we would still love to hear from you.
What you'll work on
- Designing and implementing LLM-powered features and intelligent automation workflows
- Building robust AI pipelines with proper orchestration, error handling, and monitoring
- Developing RAG (Retrieval-Augmented Generation) systems for financial data processing
- Implementing and optimizing vector search and embedding strategies
- Creating evaluation frameworks for LLM outputs and maintaining quality standards
- Building prompt management systems and optimizing LLM interactions for cost and performance
- Integrating multiple AI models and managing model versioning/deployment
- Ensuring AI safety, reliability, and compliance in financial applications
What we're looking for
- Experience with prompt engineering and prompt management systems accessible from Node.js
- Hands-on experience with AI model APIs and their Node.js SDKs (OpenAI, Anthropic, Hugging Face, Replicate)
- Knowledge of AI observability tools with Node.js integration (LangSmith, Helicone, or custom solutions)
- Proficiency with streaming architectures and Server-Sent Events (SSE) for real-time AI responses
- Understanding of AI safety, hallucination detection, and output validation techniques
- Familiarity with AI evaluation frameworks and automated testing of LLM outputs
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Remote Ai Ai Engineer Generative Ai