To develop and support research on multi-agent systems. Initial focus will be on dataset curation and managing fine-tuning workflows, with opportunity to grow into broader system development, prototyping, and research contributions.
Build and operate AI/ML infrastructure, including data pipelines, model training, LLM serving, retrieval systems, agent runtimes, evaluation, and monitoring.
Own production infrastructure across factory and cloud environments, including Linux, Docker, GPUs, CI/CD, networking, and infrastructure-as-code.
Develop scalable manufacturing data platforms and ingestion pipelines integrating tester, equipment, vendor, and reporting data.
...
Own the full lifecycle of AI-native product features — from understanding the problem and designing the experience to implementation, testing, deployment, and maintenance.
Design reliable agent systems that use the right models, tools, context, and memory, supported by practical evaluation, tracing, guardrails, and human approval.
Connect agents to customer data and external platforms through APIs, MCP, and other integration patterns, enabling them to deliver complete business outcomes rather than isolated answers.
...
Design and build end-to-end AI-powered applications, including retrieval pipelines, LLM orchestration layers, backend APIs, and user-facing interfaces.
Own the full software development lifecycle from requirements and architecture through testing, deployment, and post-launch iteration.
Integrate LLM APIs, vector databases, and retrieval-augmented generation into production applications, applying agentic orchestration where needed.
...