Senior Python Backend Engineer (m/w/d) – AI Service Operations
Are you an experienced Python Engineer who enjoys solving complex production challenges and taking ownership of critical applications? Do you thrive in environments where software engineering, cloud technologies, and AI-powered solutions come together?
We are looking for a Senior Python Backend Engineer (m/w/d) – AI Service Operations to ensure the stability, performance, and continuous improvement of modern AI-enabled applications. In this role, you will work at the intersection of backend engineering, operations, cloud platforms, and Generative AI, helping to keep business-critical services running efficiently and reliably.
Your Responsibilities
Production Operations & Incident Resolution
- Take technical ownership of AI-powered applications running in production environments.
- Monitor application health using logs, metrics, traces, and alerting systems.
- Analyze production incidents, assess their technical and business impact, and drive them to resolution.
- Perform root cause analysis across backend services, frontend applications, APIs, databases, integrations, and configurations.
- Differentiate application-level issues from platform or infrastructure-related problems and coordinate with the relevant engineering teams.
- Communicate incident status, risks, workarounds, and resolution progress to stakeholders and service management.
Python Engineering
- Review, debug, maintain, and enhance existing Python applications.
- Implement bug fixes, hotfixes, and technical improvements using established development and deployment processes.
- Create automated unit and integration tests to ensure software quality and reliability.
- Improve code quality, maintainability, resilience, and application performance.
- Support dependency management, configuration updates, and security-related enhancements.
AI & Application Support
- Troubleshoot AI-powered workflows, including LLM integrations, retrieval processes, document processing, and external AI services.
- Investigate production issues related to model responses, latency, context limitations, retrieval quality, and third-party dependencies.
- Contribute to the stability and operational excellence of Generative AI applications.
- Support go-live activities, hypercare phases, and knowledge transfer into regular operations.
Continuous Improvement & Automation
- Enhance logging, monitoring, observability, and alerting capabilities.
- Develop sustainable solutions for recurring production issues.
- Automate operational tasks and diagnostic processes wherever possible.
- Maintain technical documentation, runbooks, and troubleshooting guides.
Your Profile
Backend Engineering Expertise
- 5+ years of professional experience in Python backend development.
- Strong experience maintaining, debugging, and improving existing enterprise applications.
- Hands-on experience with FastAPI, Flask, or similar Python frameworks.
- Strong understanding of Async Python and object-oriented programming.
- Experience designing and supporting REST APIs and OpenAPI/Swagger specifications.
- Knowledge of authentication and authorization mechanisms, including OAuth2 and JWT.
- Experience with PostgreSQL, SQLAlchemy, SQL, and data modelling.
- Familiarity with Git-based development workflows, code reviews, and automated testing practices.
- Excellent debugging, troubleshooting, and root-cause-analysis capabilities.
Cloud & DevOps
- Experience supporting and operating production-grade applications.
- Hands-on knowledge of Docker and containerized environments.
- Experience working with CI/CD pipelines, ideally GitLab CI/CD.
- Strong understanding of monitoring, logging, alerting, and observability concepts.
- Experience with cloud-native and distributed systems.
- Proven ability to safely deploy fixes into production environments.
- AWS experience (ECS/Fargate, CloudWatch, S3, Load Balancing, Queues) is highly desirable.
- Experience with Terraform or other Infrastructure-as-Code solutions is a plus.
AI & GenAI Applications
- Understanding of AI and Large Language Model (LLM)-based applications from an engineering perspective.
- Experience integrating AI services through APIs.
- Knowledge of:
- Retrieval-Augmented Generation (RAG)
- Embeddings and Vector Databases
- Document Processing Pipelines
- AI Agents and Tool Calling
- Multi-step AI Orchestration WorkflowsExperience investigating AI-specific production issues and performance bottlenecks.
- Experience with Azure OpenAI or similar managed AI platforms is an advantage.
- Familiarity with LangChain, LangGraph, LlamaIndex, or comparable frameworks is a plus.
Please note: Deep machine learning research or model training expertise is not required.
Frontend & Enterprise Integration
- Ability to troubleshoot frontend-backend interactions using browser developer tools, API traces, and application logs.
- Basic hands-on experience with React and TypeScript.
- Experience with SAP integrations, SAP Gateway, EDI, Snowflake, or similar enterprise technologies is beneficial.
Qualifications
- 5+ years of professional Python backend development experience.
- Proven experience operating, maintaining, and improving production applications.
- Experience working with APIs, databases, cloud services, and distributed architectures.
- Ability to work effectively with backend, frontend, cloud, platform, and business teams.
- Degree, vocational training, or equivalent professional experience in a relevant technical field.
- Fluent English, written and spoken.
Ready to shape the future of AI operations?
Join us and play a key role in ensuring the reliability, scalability, and success of next-generation AI applications in enterprise environments.