Senior GenAI Engineer, German

This is a fully remote position, open to applicants in Romania.

📋 Description

• Design, secure, enhance, and tailor system prompts; assess the effects of prompt modifications and consistently refine LLM usage scenarios while evaluating risks and benefits.

• Create and optimize retrieval pipelines, which include document chunking, embedding generation, and ranking strategies.

• Develop and maintain solutions utilizing vector databases (such as FAISS, Weaviate, Pinecone) or Postgres with pgvector, to facilitate accurate and context-aware responses.

• Implement advanced strategies for context window optimization, memory management, and token efficiency to ensure scalable and cost-effective LLM interactions.

• Assess new LLM releases, track response quality and consistency, and create automated evaluation pipelines to measure performance across various use cases.

• Design and establish prompt injection protection, output filtering, and policy enforcement measures to guarantee safe and compliant AI behavior within enterprise settings.

• Develop and expose AI functionalities through scalable APIs, ensuring seamless integration into existing systems and workflows.

• Design and oversee serving layers for LLM applications, addressing scaling strategies, latency considerations, and reliability in both cloud and on-premises environments.

• Implement logging, monitoring, and alerting systems to ensure transparency into system performance, usage patterns, and failures.

• Create prototype and production-level Python code to support AI features, ensuring reliability and maintainability aligned with product specifications.

• Stay informed about the latest techniques in reasoning, chaining, and context optimization; contribute to discussions within the AI Labs community and share insights with the Data Science team.

⛳️ Requirements

• Proficient in the German language (B2 level or higher) is mandatory.

• Over 4 years of experience with Python and its data science ecosystem (including Pandas, NumPy, Scikit-learn).

• Demonstrated experience in prompt engineering and analysis of LLM behavior.

• Extensive practical experience with LLM integration frameworks such as LangChain or equivalent.

• Experience in designing retrieval pipelines, including chunking, embedding generation, and ranking strategies.

• Practical experience with vector databases (PG Vector, FAISS, Pinecone, Weaviate, etc.).

• Strong understanding of embeddings and semantic search.

• Experience with context window optimization, memory management, and token efficiency techniques.

• Experience in implementing prompt injection protection, output filtering, and policy enforcement measures.

• Experience in building and exposing APIs for AI systems.

• Experience with serving LLM applications, including scaling and latency optimization.

• Familiarity with deployment in cloud and/or on-premise settings.

• Experience with logging, monitoring, and system observability.

• Experience in constructing automated evaluation pipelines for LLM systems.

• Nice to have: Experience with Java or modern backend frameworks (e.g., Spring) for enterprise system integration.

• Experience with frontend frameworks (e.g., Angular) for developing or integrating AI-driven user interfaces.

• Familiarity with LLM observability tools or advanced evaluation frameworks.

• Experience with real-time or streaming inference systems.

🏝️ Benefits

• Enjoy our comprehensive benefits program that encompasses the four pillars we believe are essential for supporting our wellbeing: social, physical, emotional wellbeing, and work-life integration.

• Our wellbeing program includes medical benefits, gym support, and personalized fitness options for an active lifestyle, complemented by team events and the Healthy Habits Club.

• Our individualized approach allows us the flexibility to define the work-life dynamic that suits us best.

• We believe that in order to maintain our overall health, we must invest in our mental wellbeing as much as we do in our physical health, social connections, and achieving work-life balance.

• As a growing community in a hybrid environment, we aim to remain connected not only through the excellent work we accomplish daily but also through our shared passions and interests.