SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Monday.com is an AI work platform used by 250,000+ customers to bring people, workflows, and AI agents together on one flexible platform. Sidekick is monday.com's AI assistant, used by 2M+ people to plan, analyze, and get work done across the platform.
You will join a small, senior team that turns the latest agentic research into features that run reliably at scale. The team owns AI features end-to-end: from early prototype to production quality.
In this role, you will:
- Design, build, and ship production AI agents, including tool use, multi-step reasoning, memory and context management
- Bring state-of-the-art agentic techniques into the product
- Own agent quality by building offline evaluations (golden datasets, LLM-as-judge, regression suites) and online metrics, and drive measurable improvements
- Balance quality, latency, and cost in production with solid observability and tracing
- Work with product and design to turn open-ended goals into shipped AI features
REQUIREMENTS:
- 4+ years of software engineering experience, including hands-on work shipping AI agents or LLM-based features to production
- Hands-on experience with agent frameworks (e.g., LangGraph, Vercel AI SDK, or Claude Agent SDK) and core agentic patterns: tool calling and MCP, structured outputs, context management
- Experience evaluating AI agents and LLM-based features, both offline and online, to measure and improve quality over time
- Comfortable owning ambiguous, open-ended problems end-to-end, from exploration and prototyping to production, with limited direction
- Keeps up with a fast-moving field and adopts new techniques where they make a real difference
NICE TO HAVE:
- TypeScript/Node.js (the team's primary stack)
- High-scale data infrastructure: Kafka, Cassandra, MySQL, CDC
- Full-stack experience (React)
- Background in data science or applied ML
