Belva

• Own the AI technology strategy, architecture, and execution for a small, highly technical startup • Report directly to the CTO • Build, ship, and scale applied AI in a company where the work is central to product success • Define and execute the technical AI roadmap • Deliver technical, product, and operational outcomes tightly aligned with company goals • Hire, mentor, and manage a small team of senior generative AI engineers • Partner closely with Product Management and Project Management • Lead architecture and implementation for core AI systems, including: LLM-based workflows, RAG systems, AI agents, Evaluation and testing systems, Observability and performance monitoring, Model selection and routing, Data ingestion and retrieval systems • Own major parts of the company’s data ingestion pipeline into platform storage and analytics systems • Build infrastructure to host LLMs in the company’s new data center environment • Establish strong experimentation and measurement practices for AI features • Serve as an internal evangelist for effective use of AI agents inside the engineering organization

• Collaborate with other AI engineers, product engineers, and infra teams to build, evaluate, and iterate on AI-powered systems • Bring a deep understanding of GenAI technologies and strong software engineering skills to bear on solving real-world problems through well-architected, testable, and observable solutions.

• Design and build scalable microservices, RESTful APIs, and WebSocket-based systems • Manage and optimize NoSQL-backed data storage for performance and reliability • Develop backend services for real-time communication, high-throughput ETL, and cross-service orchestration • Implement monitoring, tracing, and alerting for production systems • Champion code quality through TDD, CI/CD pipelines, and effective code reviews • Collaborate with AI and frontend teams to deliver seamless, AI-powered features • Ensure high standards of performance, security, and maintainability