Senior AI Engineer (m/f/d)

Jobgether; Deutschland; Hybrid; EUR 90.000 - 130.000; Vollzeit

Benefits dieser Stelle

Home-office setup budget $500

Annual learning budget $1000

Visa and relocation support

Flexible work-from-home arrangement

Production-scale AI initiatives

Zusammenfassung

Jobgether is partnering with a Germany-based partner company to hire a Senior AI Engineer (m/f/d). You will design, build, deploy, and iterate LLM-powered features in production, addressing RAG, embeddings, agents, tool calling, and AI orchestration. You’ll work across Product, ML, and Engineering to deliver scalable AI solutions.

You will implement robust evaluation, observability, and cost controls while maintaining high performance and reliability in a fast-moving product environment.

Qualifikationen

• Hands-on experience shipping LLM-powered features into production.
• Practical experience with RAG, embeddings, vector search, agents, and tool calling.
• Strong understanding of production LLM considerations: evaluation, observability, latency and cost.
• Experience improving AI features based on telemetry and user feedback.
• Strong software engineering background: APIs, backend services, distributed systems.
• Full-stack exposure with Angular/TypeScript/Python/Node.js is a plus.
• Experience with AWS, CI/CD and modern cloud environments.

Aufgaben

• Architect, develop, deploy, and maintain production-grade LLM capabilities in customer-facing products.
• Build backend services, APIs, integrations, and infrastructure connecting AI to product features.
• Contribute to full-stack development and user-facing experiences where needed.
• Implement production-ready patterns involving LLMs, RAG, embeddings, agents, and tool calling.
• Design reusable components and patterns to improve velocity, consistency, and maintainability.
• Establish evaluation, observability, monitoring, and feedback loops for AI features.
• Monitor and optimize AI systems for quality, latency, reliability, scalability, and cost.
• Investigate production issues, analyze telemetry, and improve AI functionality from feedback.
• Collaborate with Product, ML, and Engineering to translate problems into practical AI solutions.
• Prototype quickly and turn experiments into robust production systems.
• Contribute to architecture decisions and long-term technical sustainability.

Kenntnisse

LLM integration

RAG patterns

Embeddings

Agent systems

Tool calling

Distributed systems

Backend API design

AWS / cloud infra

CI/CD

Frontend basics

Tools

Docker

AWS

GCP

Azure

CI/CD pipelines

Jobbeschreibung

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Engineer (m/f/d) based in Germany.

This is a hands-on engineering opportunity focused on bringing AI-powered capabilities into real-world products and production workflows. You will design, build, deploy, and continuously improve LLM-powered features within a large-scale technology environment. The role combines strong software engineering with practical expertise in RAG, embeddings, agents, tool calling, and AI orchestration. You will work closely with Product, ML, and Engineering teams to turn complex business challenges into pragmatic and scalable AI solutions. Beyond implementation, you will help establish robust evaluation, observability, monitoring, and feedback practices for production AI systems. The environment is fast-moving and product-focused, offering significant ownership and opportunities to experiment, iterate, and ship. This role is particularly suited to an engineer who enjoys taking AI capabilities from prototype through reliable, maintainable production systems.

Accountabilities:

• Architect, develop, deploy, and maintain production-grade LLM capabilities integrated into customer-facing products and internal workflows.
• Build backend services, APIs, integrations, and supporting infrastructure that connect AI capabilities with product functionality.
• Contribute to full-stack and user-facing development where required, helping deliver complete AI-powered product experiences.
• Implement production-ready patterns involving LLMs, RAG, embeddings, vector search, agents, and tool calling.
• Design reusable components, abstractions, and engineering patterns that improve development velocity, consistency, and maintainability.
• Establish and improve evaluation frameworks, observability, monitoring, and feedback loops for AI-powered features.
• Monitor and optimize AI systems for quality, latency, reliability, scalability, and inference cost.
• Investigate production issues, analyze telemetry, and continuously improve AI functionality based on system performance and user feedback.
• Collaborate closely with Product, ML, and Engineering stakeholders to translate product challenges into practical AI solutions.
• Rapidly prototype and validate new ideas, then transform successful experiments into robust and maintainable production systems.
• Contribute to engineering decisions around architecture, trade-offs, scalability, and long-term technical sustainability.

Requirements:

• Demonstrated hands-on experience building and successfully shipping LLM-powered features or applications into production.
• Practical experience with technologies and patterns such as RAG, embeddings, vector search, agentic systems, LLM APIs, orchestration, and tool calling.
• Strong understanding of production LLM considerations, including evaluation, observability, failure modes, latency, reliability, and cost management.
• Experience improving AI features based on telemetry, evaluation results, production behavior, or user feedback.
• Strong software engineering background with experience designing APIs, backend services, and production-grade distributed systems.
• Full-stack development experience with technologies such as Angular, JavaScript/TypeScript, Python, Node.js, or comparable technologies is a strong advantage.
• Ability to write clean, maintainable, well-structured code and take ownership of solutions from implementation through production.
• Willingness and ability to contribute across backend services, AI infrastructure, and user-facing product functionality.
• Experience working with AWS or comparable cloud infrastructure, CI/CD pipelines, and production environments.
• Strong product mindset with a bias toward shipping, rapid iteration, pragmatic problem-solving, and measurable outcomes.
• Comfortable working in an environment characterized by ambiguity, rapid change, and evolving requirements.
• Strong communication and collaboration skills, with the ability to work effectively with Product, ML, and Engineering teams.
• Ability to challenge requirements constructively, communicate technical trade-offs, and translate AI complexity into practical product solutions.
• A maintainability- and reuse-oriented mindset, with a focus on building production systems rather than isolated demonstrations.
• Experience with multi-agent systems, MCP, guardrails, moderation, safety checks, prompt and context management, routing, caching, or fallback strategies is a plus.
• Experience with Docker and cloud platforms such as AWS, GCP, or Azure is beneficial.
• Experience with modern frontend development and customer-facing web applications is an advantage.
• This role is focused on applied AI engineering rather than heavy model training, academic research, custom ML algorithm development, or theoretical optimization work.

Benefits:

• Highly visible role with direct access to senior leadership and meaningful influence on product and engineering decisions.
• Strong career growth and continuous learning opportunities in applied AI and software engineering.
• Opportunity to work alongside experienced technology, product, and industry professionals on high-impact AI initiatives.
• International and multicultural working environment with colleagues distributed across multiple countries.
• Flexible work-from-home arrangement.
• $500 home-office setup budget to support a productive remote working environment.
• $1,000 annual learning and development budget to support professional growth and skills development.
• Visa and relocation support where required.
• Opportunity to work on production-scale AI applications and modern LLM technologies.
• Significant ownership and autonomy in taking AI solutions from experimentation through deployment and continuous improvement.
• Competitive compensation aligned with experience, skills, and market standards.

How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.