Veeva Systems is a mission-driven organization and pioneer in industry cloud, helping life sciences companies bring therapies to patients faster. The role involves architecting, building, and validating the next generation of Nitro AI Agents, focusing on designing complex workflows and ensuring system reliability in a life sciences environment.
Responsibilities:
- Agentic Architecture: Proven experience building scalable AI orchestration layers that drive operational workflows, ranging from high-precision Text-to-SQL agents to complex multi-agent systems capable of tool-calling, event orchestration, and autonomous self-correction
- Model Strategy: Choose and configure the optimal LLMs based on cost, reasoning depth, and latency
- Hybrid Data Systems: Build scalable bridges between Relational Databases (Postgres/Java) and Vector Stores, using metadata strategies like PageIndex to ensure data stays synchronized and searchable
- Text-to-SQL Agents: Develop high-precision agents that translate natural language into complex SQL, featuring self-correction loops to handle large enterprise schemas accurately. Choose appropriate RAG approach for semantic embedding and retrieval
- Automated Validation: Develop, implement, and maintain scalable automated evaluations to ensure agent behavior remains consistent across model updates and feature releases
Requirements:
- 2+ years of proven experience building scalable AI orchestration layers that drive workflows, ranging from precision Text-to-SQL agents to complex multi-agent systems capable of tool-calling, event orchestration, and autonomous self-correction
- 7+ years of experience building and deploying distributed systems that handle high concurrency, rate-limiting, and asynchronous task queues using Java, Spring, and Python. Optimize AI orchestration for performance, scalability, and efficiency
- Expert at building high-precision RAG systems across structured relational data and unstructured documents, utilizing vector databases to enable accurate retrieval across large-scale enterprise datasets
- Experience building pipelines to measure complex AI agent performance using key metrics like task success rate, accuracy, and output quality
- Stay updated on the latest AI and machine learning advancements, research papers, and tools, incorporating them into AI development projects
- Demonstrated ability to mentor team members and contribute to a positive and high-performing team environment
- Bachelor's degree in Computer Science, Data Science, Machine Learning, or a related technical field
- High work ethic, high integrity, and a 'do the right thing' mindset
- Applicants must have the unrestricted right to work in the United States. Veeva will not provide sponsorship at this time
- Familiarity with the unique data privacy and regulatory requirements of the life sciences industry