AI Operations Engineer
Posted Updated
Description
- This is a builder role with an operator’s mindset
- You’ll find the highest-leverage work across Sales, Customer Success, Marketing, Support, Finance, Risk, Product, and Operations, and own it end to end, from first conversation to production
- Some weeks you’ll write code; others you’ll run a workshop or redesign a process with a team
- Everyone at Coast uses Claude and builds their own skills
- You build what they can’t: autonomous agents, and the foundation that makes everyone’s skills better
- In your first six months, you’ll ship three or more agents that teams rely on daily, each backed by evals that show it improving month over month
- You’ll drive measurable gains in Coast’s operating efficiency, tracked in hours saved
- Find and prioritize the work. Sit with teams, map their workflows, and size the time saved. Turn what you find into a ranked backlog with the AI Lead
- Build autonomous agents. Ship event-driven agents that do multi-step work across our stack. You’ll own the engineering off-the-shelf tools can’t do:
- Loop and orchestration: design agent loops, sub-agent handoffs, and when to act alone or escalate to a human
- Memory and context: model shared memory as a knowledge graph, and decide what each agent sees, remembers and forgets
- Custom tooling: build the tools our agents need
- Traces and evals: trace every run, score outputs against test sets built from real outcomes, and prove each version beats the last
- Measure impact. Define success metrics for each build, track adoption and time saved, and report results to leadership
- Run what you ship. Own reliability, latency and cost in production, and catch regressions before users do. Partner with Security and IT on access, audit trails and the handling of sensitive data
- Enable the company. An AI-native company runs on self-service, and self-service needs solid infrastructure. You’ll architect the shared foundation the rest of Coast builds on: knowledge bases, application databases, templates, tools, and connectors. Then you’ll help people use it through training, office hours and hackathons, and grow a network of AI champions
- Stay on the cutting edge. Try new models and tools as they land, measure them against what we run today, and keep raising the bar on everything you’ve built
Benefits
- Medical, dental, and vision coverage
- Meaningful stock options
- Flexible vacation policy
- 2–5 years in operations, product, solutions or forward-deployed engineering, internal tools, or a similar role at a fast-moving company
- Hands-on fluency with Claude Code, Cursor or similar coding agents, plus LLM tooling such as prompt design, tool use and MCP
- High agency: you spot inefficient processes and fix them without waiting to be asked
- Clear communication with non-technical teammates. You can teach as well as build
- Experience with evals: building test sets, scoring outputs and using the results to improve an agent
- A track record of shipping AI workflows or automations that people use every day. Show us what you built
- Comfort writing and reading code: SQL, plus Python or TypeScript scripting, APIs and webhooks
- You’ve built at least one agent with persistent memory or a feedback loop that made it better over time
- Startup experience, especially at an AI-native company
- Background in fintech, payments or another regulated industry
- Experience with guardrails or monitoring for AI systems
- A software engineering background
- Experience building with the MCP servers or APIs for tools like Salesforce, Notion, Slack and Gmail
Skills
Sign in to read and join the discussion.