Responsibilities
- Create and improve AI agents powered by large language models to coordinate engineering teams, identify project risks, and generate formal documentation such as proposals and status reports.
- Lead development of the agent orchestration system, currently using LangChain DeepAgent, and assess new technologies to determine if updates or replacements are necessary.
- Develop reliable methods for agents to interact with external platforms including project tracking, CAD, PLM, and communication tools through API integrations.
- Optimize prompts, chains, and data retrieval techniques to enhance the accuracy and effectiveness of AI agents across complex hardware development environments.
- Construct evaluation systems to monitor agent performance, including traceability, cost efficiency, response speed, and automated quality assessments.
- Design streaming interfaces that provide users with live updates, transparent decision-making processes, and proactive notifications.
- Keep pace with evolving LLM capabilities, agent frameworks, and supporting tools, and provide practical insights to guide team strategy.
- Work closely with frontend developers to shape user experiences for AI features and with backend teams to refine data flows and API structures.
- Participate in key decisions about AI system architecture, contribute to code reviews, and help uphold engineering standards.
Compensation
Competitive salary and benefits package
Work Arrangement
Hybrid work model with flexibility based on project needs
Team
Part of a specialized AI engineering team embedded within a manufacturing and product development environment
Responsibilities
- Designing, building, and iterating on LLM-powered agents that coordinate across engineering disciplines, surface project risks, and generate structured deliverables (proposals, SOWs, status reports)
- Owning the agent orchestration layer (currently LangChain DeepAgent) and continuously evaluating whether to extend, replace, or supplement it as new frameworks and patterns emerge
- Implementing robust tool-use patterns that connect agents to external systems (project management tools, CAD/PLM platforms, communication channels) via APIs and integrations
- Designing and tuning prompts, chains, and retrieval strategies to maximize agent reliability, accuracy, and usefulness across diverse hardware project contexts
- Building evaluation and observability infrastructure for agent performance, including tracing, cost tracking, latency monitoring, and automated quality benchmarks
- Developing streaming agent interfaces that surfacing real-time progress, reasoning transparency, and proactive alerts to end users
- Staying current with rapid advances in LLMs, agent frameworks, and related tooling, and translating that awareness into actionable recommendations for the team
- Collaborating with frontend engineers on the UX of AI-powered features and with backend engineers on data pipelines and API design
- Contributing to AI architecture decisions, code reviews, and engineering best practices
Available for qualified candidates
