Staff AI Engineer – Agent Platform
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Staff AI Engineer building wingmaite’s agent platform for German Mittelstand knowledge. Designing production LLM agents, evaluations, and end-to-end backend features.
Responsibilities:
- 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:
- 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:
- 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
Similar Jobs
Senior AI Architect
Senior AI Architect designing PointClickCare’s shared AI platform for healthcare software teams. Establishing agentic architecture, governance, observability, and reusable engineering patterns.
Senior AI Architect
Senior AI Architect designing PointClickCare’s scalable AI platform for healthcare providers. Enabling engineering teams to build agents, MCP servers, and GenAI solutions.
Principal AI Engineer
Principal AI Engineer defining LLM and agentic AI architecture for Rapid7’s cybersecurity platform. Building scalable models, inference systems, and evaluation standards for security products.
Senior AI Engineer
Senior AI Engineer building and evaluating reinforcement-learning language models for EnableComp. Owning experiments, datasets, and model evaluations while complying with HIPAA data policies.
Cybersecurity Staff Engineer – AI Security
Cybersecurity Staff Engineer securing The Home Depot's AI gateway, agents, and MCP traffic. Deploying Prisma AIRS, Google Model Armor, and DLP protections.
Director, Applied AI Engineering – Life Sciences Markets
Director building and leading production AI systems for Vi’s pharmaceutical market analytics platform. Owning ML/LLM architecture, delivery, evaluation, deployment, and client-facing product strategy.
Software Developer, AI Platforms
Software Developer building React, Python, and AI applications for FWI’s defense customers. Securing platforms on Microsoft 365 GCC High and Azure Government.
AI Engineer
AI Engineer building C#/.NET and Azure AI agents for AnywhereNow’s enterprise dialogue-management products. Developing MCP integrations and production-ready Microsoft ecosystem solutions.
AI Engineer
AI Engineer building C#/.NET and Azure-based enterprise AI agents for AnywhereNow’s dialogue-management platforms. Developing secure MCP integrations and production-ready intelligent systems.
Senior AI Engineer
Senior AI Engineer designing, deploying, and optimizing production AI systems for Rearc’s enterprise clients. Building agents, evaluation frameworks, and enterprise integrations.
Senior AI Engineer – Full Stack
Senior AI Engineer transforming business ideas into production AI applications for Nortal, a digital transformation consultancy. Building agentic workflows, enterprise data integrations, safety systems, and AI optimization layers.
Senior Agentic AI Engineer
Senior Agentic AI Engineer architecting autonomous AI systems and RAG platforms. CodeRoad partners with US companies to modernize and scale business technology.
Senior Agentic AI Engineer
Senior Agentic AI Engineer designing production-ready agentic AI systems for CodeRoad’s end-to-end software development services. Building AWS, RAG, MCP, and multi-agent solutions.
AI Engineer
Agentic AI Engineer building LangGraph-based multi-agent systems for CodeRoad, a technology execution partner delivering product, platform, modernization, and AI engineering. Optimizing LLM workflows, observability, evaluation, and security.
AI Engineer
Agentic AI Engineer building production-grade agents and RAG applications for CodeRoad. Deploying and monitoring LLM solutions for US client teams from Latin America.
Senior AI Engineer
Senior AI Engineer building secure, scalable GenAI systems for Factored, which helps U.S. companies build AI, ML, and data teams with LATAM talent. Owning architecture, deployment, and optimization.
AI Engineer
AI Engineer building ServiceTitan’s Agent OS platform for contractor business operations. Developing safe agent runtimes, tools, memory, approvals, evaluations, and observability.
AI Engineer
AI Engineer building Agent OS runtime, tools, memory, trust, and evaluation infrastructure. Powering safe AI agents for ServiceTitan’s contractor-management platform.
Senior Software Engineer, AI Platform
Senior Software Engineer building orchestration, evaluation, and guardrail infrastructure for Kinetic’s AI agents. Supporting technology-driven workers’ compensation solutions for employers and insurers.
Founding AI Lead, Human Behavior Simulation
Founding AI Lead building human behavior simulation models for Populix, Indonesia’s market and policy research consultancy. Leading Singapore client deployments, research, and eventual local team scaling.