- Design and integrate LLM-based solutions, focusing on RAG implementations and optimal architecture patterns
- Lead rapid experimentation and prototyping of AI features, conducting proof of concepts to validate solutions
- Drive cost optimization for AI implementations through efficient architecture design
- Work closely with product, engineering, and customer experience teams to develop AI solutions
- Build and optimize prompt engineering workflows to enhance user experiences
- Implement robust error handling and monitoring for AI systems
- Guide technical discussions around AI architecture decisions
- Mentor team members and champion innovation in AI development
- 5+ years of backend engineering experience with TypeScript/Node.js or Python
- Experience with LLM integrations (OpenAI, Anthropic, Azure OpenAI) and familiarity with orchestration frameworks like LangChain or LlamaIndex
- Experience/familiarity with real-time event-driven and streaming systems
- Working knowledge of prompt engineering, RAG, and vector databases
- Experience with API design and microservices architecture
- Track record of rapid prototyping and experimentation
- Strong cross-functional collaboration and communication skills
- You thrive in a fast-paced environment with evolving requirements
- You balance quick experimentation with production-ready code
- You're skilled at navigating ambiguity and driving projects to completion
- You collaborate effectively with diverse stakeholders
- You make thoughtful architectural decisions, balancing innovation with constraints
- You focus on business impact and user experience
Nice to Have:
- Experience with conversational AI and voice agent development
- Knowledge of autonomous agent architectures and workflows
- Background in data pipeline design and ETL processes
- Experience building low-latency, real-time AI systems
- Familiarity with AI agent orchestration frameworks
- Understanding of multi-agent systems and communication patterns
- Knowledge of AI system cost optimization
TBD