Senior GEN-AI Engineer (Data & Platform) - Germany
Role details
Job location
Tech stack
Job description
We are seeking a Senior GEN-AI Engineer with a Data & Platform focus. You will design, build, and operate GEN-AI powered, data-intensive systems that process and learn from large-scale event streams. This role is production-oriented: you'll ship reliable LLM features, prove they work via rigorous evaluation, and continuously improve quality through context engineering.
This is not a research-only role. You will work on systems where LLMs interact with business-critical workflows, and where quality, latency, observability, and operational reliability matter.
What you can expect:
- Build and maintain production-grade GEN-AI services in Python.
- Write clean, maintainable, and efficient code.
- Optimize applications for performance, reliability, and scalability.
- Design systems that process, enrich, and learn from real-time event streams.
- Work with data pipelines, message queues, retrieval systems, and streaming architectures.
- Build reliable context and retrieval layers for LLM-powered products.
- Improve LLM quality through context engineering, evaluation, observability, and feedback loops.
- Design systems with idempotency, retries, deduplication, backpressure, and failure recovery in mind.
- Collaborate closely with backend, data, product, and infrastructure teams
Requirements
Do you have experience in Python?, Do you have a Master's degree?, * Bachelor's degree in Computer Science, Engineering, or a related field.
- 1+ years of experience with GEN-AI projects.
- 5+ years of experience with the Python programming language.
- Proven experience building data-intensive applications.
- Hands-on experience shipping production systems, not only prototypes or notebooks.
- Experience with event-driven systems, message queues, or streaming architectures.
- Experience with Kubernetes or cloud-native infrastructure.
- Strong understanding of observability, metrics, logging, alerts, and production debugging.
- Ability to reason about reliability topics such as idempotency, retries, duplicate events, backpressure, latency, and failure modes.
- Experience with distributed systems, including design patterns for scalability, fault tolerance, data consistency, and partitioning in large-scale production environments.
- Experience with data retrieval techniques.
- Experience with DSPy, GEPA, or other LLM optimization/evaluation techniques is a plus
Experience with some of the following is a strong plus:
- RisingWave or other streaming databases
- Apache Kafka or similar event-streaming systems
- Apache Iceberg, data lakes, lakehouse architectures, or Ice Lake-style platforms
- Airflow or similar workflow orchestration tools
- PostgreSQL or other relational databases at scale
- Vector databases or hybrid search
- Real-time data processing
- Data retrieval systems
Benefits & conditions
- Competitive salary based on performance and experience
- Chance of earning Klar stock options
- 26 days of paid vacation per year
- Computer devices
- Wellhub subscription to offer mental and physical health
- Sponsored coaching and therapy sessions via Modern Health
- Training budget to upskill your learning
- Health insurance & Pension scheme
- BVG Corporate ticket
- Berlin office if you prefer to work onsite
- International work environment with amazing and highly skilled people
- A world class team that helps you evolve your skills in areas you're interested in
Klar is a safe place for everyone!
We trust our highly skilled and diverse team and we're committed to creating a welcoming and inclusive environment for new talents to flourish. We value diversity and welcome all applications regardless of gender, nationality, ethnic and social origin, religion/belief, physical abilities, age, sexual orientation and identity.
Should you require any accommodations through the recruitment process, please don't hesitate to let us know how we can help!