Staff AI Engineer – Agent Platform

wingmaite

. Design agents that plan, use tools, handle multi-step work, and determine where people need to step in .

Posted 11/3/2026full-timeRemoteLeadWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and deploying multi-step, tool-using LLM agents, with a strong focus on collaboration across design, product, engineering, and AI. Proficient in Python and TypeScript, with experience in PostgreSQL and AI coding tools, ensuring effective communication of technical concepts to non-engineers.

Highest-signal resume keywords

Multi-Step Tool-Using LLM Agent DeploymentPython ProgrammingTypeScript/Node ProficiencyPostgreSQL Data ModelingTechnical Direction Setting

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Multi-Step Tool-Using LLM AgentsPythonTypeScriptPostgreSQLData ModelingAI Coding ToolsLangGraphNestJSMCP IntegrationKnowledge Graphs

Soft Skills

Clear Specification WritingTechnical DebateCollaborationUser-Centric Problem SolvingAdaptability

Tools & Technologies

Claude CodeAWS BedrockVertex AILLM Observability ToolsLangfuse

Industry Keywords

Architectural PatternsQuality MonitoringCost EvaluationStakeholder CollaborationSystem Reliability

Tech Stack

Tools & technologies

AWSNode.jsPostgresPythonTypeScript

About the role

Key responsibilities & impact

Design agents that plan, use tools, handle multi-step work, and determine where people need to step in
Build reusable components for new use cases
Connect agents to company knowledge and work with stakeholders to define what that knowledge should contain
Improve answer reliability, source citation, access control, and safe non-action decisions
Build evaluations and monitor quality and cost
Keep model choices up to date
Ship features end to end from the agent through to the backend
Set architectural patterns, document decisions, maintain current specifications, and review designs with engineering, product, and design
Collaborate as one team across design, product, engineering, and AI from initial problem definition through production
Work closely with the CTO as a technical sparring partner

Requirements

What you’ll need

You've shipped multi-step, tool-using LLM agents to production (LangGraph or similar)
You know when sub-agents help, how to build good evals, and why retrieval fails
Fluent in Python and productive in TypeScript/Node (NestJS is a plus)
PostgreSQL and data modeling
You use AI coding tools such as Claude Code every day
You write clear specs and can explain trade-offs to people who aren't engineers
Fluent English (C1–C2)
Nice-to-have: You've connected agents to tools and data through MCP
Nice-to-have: You've worked with knowledge graphs or other ways of modeling how people, work and information relate
Nice-to-have: You've run models in production on AWS Bedrock or Vertex AI
Nice-to-have: You've traced and debugged agents with LLM observability tools such as Langfuse
Nice-to-have: You speak German
You've set technical direction beyond your own work, and others build on your patterns
You start from what users need and what could go wrong, then choose the tools
You care whether the system still makes sense in a year
You're happy to do backend work when a feature needs it
You want influence through your work, not through a title
You like working with designers and product people
You enjoy technical debate and change your mind when the other argument is better

Benefits

Comp & perks

Permanent employment
40 hours/week
30 days of annual leave
Flexible remote setup
Learning & development opportunities
Generous vacation & workation budget
Technical ownership of the platform at the core of wingmaite's product