AI Application Engineer – AI Products (LLM & RAG) (m/f/d)

Academic Key; Berlin; Hybrid; EUR 70,000 - 110,000; Full time

Benefits offered by this job

Mobility package

Gym subsidy

Insurance & Pension Scheme

Corporate Savings Plan

KiTa and Childcare Allowance

Job summary

Machine Learning Reply in Berlin is hiring an AI Application Engineer to build user-facing AI applications and scalable products using LLMs, RAG and modern AI frameworks. You will work across AI engineering, backend development, product teams and cloud deployment to ship production-ready AI systems that create real business value.

The role combines design, implementation and deployment of AI-powered features, collaborating with customers and engineers, with emphasis on reliable, scalable

Qualifications

• Degree in Computer Science, Software Engineering, Data Science or a comparable technical field.
• Convincing communication and presentation skills in German and English.
• Strong programming skills in Python and modern backend frameworks.
• Experience building applications using AI, machine learning or generative AI technologies.
• Familiarity with Retrieval-Augmented Generation (RAG) and vector databases.
• Familiarity with cloud platforms such as AWS, Azure or GCP.

Responsibilities

• Design and develop AI applications, such as enterprise assistants, AI copilots, semantic search platforms and intelligent automation systems.
• Build LLM-powered applications using Retrieval-Augmented Generation (RAG) and modern AI frameworks.
• Develop end-to-end AI products, integrating LLM APIs, enterprise data sources and backend services.
• Design scalable AI microservices and APIs to integrate AI capabilities into enterprise platforms.
• Implement vector search, embeddings pipelines and knowledge retrieval systems.
• Rapidly prototyping AI product features and proof-of-concepts and evolving them into production systems.
• Collaborating closely with product managers, designers, AI engineers and enterprise customers to develop impactful AI solutions.
• Deploying AI systems to cloud platforms and production environments using modern DevOps practices.
• Ensuring reliable, scalable and observable AI services through CI/CD pipelines, monitoring and containerized deployments.

Skills

Python

Backend frameworks

AI/ML technologies

German & English

Education

CS/Software Engineering/Data Science degree

Tools

LangChain

LlamaIndex

HuggingFace

Docker

CI/CD

Kubernetes

Vector databases

Job description

AI Application Engineer – AI Products (LLM & RAG) (m/f/d)

Machine Learning Reply · Berlin

Abroad

At Machine Learning Reply, we help organizations turn cutting-edge AI technologies into real-world applications and scalable digital products. To strengthen our team, we are looking for an AI Application Engineer who enjoys building AI-powered solutions and intelligent product features using modern machine learning and generative AI technologies. While our GenAI Engineers focus on model development and AI architectures, AI Application Engineers focus on building user-facing AI applications and turning AI capabilities into scalable products. In this role, you will work at the intersection of AI engineering, backend development, product development and cloud deployment, building production-ready AI systems that create real business value.

Tasks

• Designing and developing AI applications, such as enterprise assistants, AI copilots, semantic search platforms and intelligent automation systems
• Building LLM-powered applications using Retrieval-Augmented Generation (RAG) and modern AI frameworks
• Developing end-to-end AI products, integrating LLM APIs, enterprise data sources and backend services
• Designing scalable AI microservices and APIs to integrate AI capabilities into enterprise platforms
• Implementing vector search, embeddings pipelines and knowledge retrieval systems
• Rapidly prototyping AI product features and proof-of-concepts and evolving them into production systems
• Collaborating closely with product managers, designers, AI engineers and enterprise customers to develop impactful AI solutions
• Deploying AI systems to cloud platforms and production environments using modern DevOps practices
• Ensuring reliable, scalable and observable AI services through CI/CD pipelines, monitoring and containerized deployments

Benefits

• Work in an open and collaborative environment within the global Reply network and build next-generation AI applications and intelligent digital products
• Collaboration with interdisciplinary teams including AI engineers, software developers and data scientists across industries such as Banking, Insurance, Automotive and Retail
• A very active social program including paid training, conferences, communities of practice, hackathons and Reply XChange
• Monetary Benefits include: Mobility package, Gym subsidy & WellPass, Insurance & Pension Scheme, Corporate Savings Plan, KiTa and Childcare Allowance
• Flexible work arrangement between home office, EU-wide workation options, on site office-work in our downtown Munich office with access to Stammstrecke, and client on site visits

Requirements

• Degree in Computer Science, Software Engineering, Data Science or a comparable technical field
• Convincing communication and presentation skills in German and English in order to participate in workshops of both languages
• Strong programming skills in Python and modern backend frameworks
• Experience building applications using AI, machine learning or generative AI technologies
• Familiarity with Retrieval-Augmented Generation (RAG) and vector databases
• Familiarity with cloud platforms such as AWS, Azure or GCP
• Engaging directly with enterprise clients to understand their business challenges and identify high-impact opportunities for AI-driven solutions

Nice to have

• Experience running technical workshops or facilitating solution design sessions
• Experience developing APIs, microservices and scalable backend systems, including vector databases
• Experience with containerization and DevOps practices (Docker, CI/CD pipelines, Kubernetes or similar)
• Experience with frameworks such as LangChain, LlamaIndex or HuggingFace
• Experience deploying AI services in cloud environments
• Knowledge of AI observability, monitoring, and evaluation of LLM systems

Example projects you may work on

• Enterprise AI knowledge assistants
• AI copilots for internal business tools
• Semantic search platforms for enterprise data
• Document intelligence systems powered by LLMs
• AI agents and automation systems for enterprise workflows