People In AI is a venture-backed technology platform building next-generation AI systems for complex workflows. The role involves owning the design and deployment of production AI systems, including building multi-agent systems and developing scalable infrastructure for real-world applications.
Responsibilities:
- Build and scale multi-agent systems powering copilots and workflow automation
- Design end-to-end AI architectures across retrieval, reasoning, tool use, and validation
- Develop orchestration frameworks, including memory, state management, and tool routing
- Own evaluation frameworks focused on reasoning quality, hallucination reduction, and correctness
- Deploy and maintain distributed, low-latency AI systems in production
- Contribute to platform-level decisions across model serving, infrastructure, and system design
Requirements:
- Proven experience shipping LLM-powered or AI products into production environments
- Strong experience with multi-agent systems and orchestration frameworks
- Deep understanding of RAG, memory systems, and tool-calling architectures
- Hands-on experience with post-training techniques (LoRA, DPO, GRPO, or similar)
- Strong Python and distributed systems engineering background
- Experience building and operating systems in cloud production environments
- Ability to operate autonomously in a fast-paced, low-structure environment