Staff Engineer

Jobtailor; Deutschland; Vor Ort; EUR 120.000 - 180.000; Vollzeit

Zusammenfassung

Jobtailor seeks a Senior AI Platform Architect to lead the design, delivery, and operation of production-grade AI tools and internal platforms. You will own complex MCP-based integrations, context management, and secure, scalable infrastructure across backend services and user interfaces.

You will translate ambiguous business problems into robust architectures, drive platform initiatives, and mentor teams through code reviews and guidance while ensuring reliability and observability in a

Qualifikationen

• 8+ years of professional software development experience with leadership impact.
• Hands-on experience building AI-enabled applications in production.
• Strong familiarity with MCP or similar tool-use protocols, agents, context management, and LLM integrations.
• Proven track record building internal tools, developer platforms, or enterprise systems.
• Deep backend engineering expertise in Ruby or Python.
• Strong systems-design fundamentals including APIs, distributed systems, and data flows.
• Practical AWS/DevOps experience with CI/CD, containers, serverless infra, observability, and IaC.
• Ability to drive initiatives through ambiguity and communicate credibly at staff level.
• Bonus: experience with React, TS, GraphQL, and related tooling.

Aufgaben

• Architect and build production-grade internal AI tools and shared platform capabilities.
• Lead technical design and delivery of AI integrations with MCP, agentic workflows, and context layers.
• Translate ambiguous problems into architecture and actionable implementations.
• Develop and maintain infra connecting models with internal systems, APIs, and workflows.
• Own reliability, scalability, observability, and security of production AI systems.
• Build internal experiences across backend services, infrastructure, and user interfaces.
• Collaborate with engineers and business owners to deliver high-value workflows.
• Evaluate emerging AI models/frameworks and define adoption strategies.
• Shape the technical roadmap by identifying reusable platform opportunities.
• Provide technical leadership through reviews, pairing, and guidance.

Kenntnisse

Software leadership

AI-enabled apps

MCP protocols

Backend Ruby/Python

Systems design

AWS & DevOps

Independent work

Communication

React/TS/GraphQL

Tools

Kubernetes

GitLab CI/CD

GraphQL

n8n

Temporal

Cloudflare Workers

HIPAA/SOC 2

Jobbeschreibung

• Architect and build production-grade internal AI tools and shared platform capabilities
• Lead technical design and delivery of complex AI integrations involving MCP, agentic workflows, context layers, model gateways, and workflow automation
• Take ambiguous business problems from discovery and architecture through implementation, deployment, measurement, and ongoing operation
• Develop and maintain infrastructure connecting approved models with internal systems, data, APIs, and user workflows
• Own reliability, scalability, observability, and security of production AI systems, including model routing, evaluation, access control, and sensitive-data handling
• Build internal experiences across backend services, infrastructure, and user-facing interfaces
• Collaborate with GSD teammates, engineers, and business owners to translate high-value workflows into maintainable solutions
• Evaluate emerging AI models, frameworks, and patterns and recommend what to adopt, adapt, or avoid
• Shape the technical roadmap by identifying reusable platform opportunities and connecting engineering investments to measurable business impact
• Provide technical leadership through code reviews, pairing, guidance, documentation, office hours, and engineering discussions

Requirements

• 8+ years of professional software development experience, including demonstrated impact as a technical leader on complex production systems
• Hands-on experience building and operating AI-enabled applications in production
• Strong familiarity with MCP or comparable tool-use protocols, agents, context management, and LLM integrations
• Track record of building internal tools, developer platforms, or enterprise systems adopted by real users and producing measurable operational impact
• Deep backend engineering expertise in Ruby, Python, or a comparable language
• Strong systems-design fundamentals, including APIs, integrations, distributed systems, data flows, authentication, authorization, and pragmatic architectural trade-offs
• Practical cloud and DevOps experience in AWS or a comparable environment, including CI/CD, containers, serverless infrastructure, observability, and infrastructure as code
• Ability to work independently through ambiguity and drive substantial initiatives to completion
• Clear, credible communication and Staff-level influence
• Bonus: Experience with React, TypeScript, GraphQL, n8n, Temporal, Langfuse, GitLab CI/CD, Kubernetes, Cloudflare Workers, HIPAA, or SOC 2

Core Competencies

Demonstrates extensive experience in architecting and building production-grade AI tools and systems, with a strong focus on backend engineering, cloud infrastructure, and technical leadership. Proven ability to translate complex business problems into scalable, reliable solutions while ensuring security and observability.

Highest-signal resume keywords

• AI-Enabled Application Development
• Backend Engineering in Ruby or Python
• Cloud and DevOps Experience in AWS
• MCP or Comparable Tool-Use Protocols
• Systems-Design Fundamentals

ATS Optimization Keywords

Hard Skills

• AI Tool Architecture
• Backend Development
• API Design
• Distributed Systems
• Data Flow Management
• Authentication and Authorization
• Infrastructure as Code
• CI/CD Practices
• Model Integration
• Workflow Automation

Soft Skills

• Clear Communication
• Technical Leadership
• Independent Problem Solving
• Collaboration

Industry Keywords

• MCP
• LLM Integrations
• HIPAA
• SOC 2

Tools & Technologies

• AWS
• GitLab CI/CD
• Kubernetes
• React
• TypeScript
• GraphQL
• N8n
• Temporal
• Cloudflare Workers