Delaplex logo

LLM Engineer

Delaplex
5 days ago
Contract
On-site
Munich, Bavaria, Germany
Generative AI

Role Overview: 

The LLM Engineer will join an existing development team to build and ship LLM-powered features in a complex, production application used at scale. This is a hands-on, full-stack role spanning backend services, APIs, and the LLM systems (retrieval, agents, evaluation) that power them. We are looking for a skilled AI Engineer/Software Engineer with experience in Python, Java, Elasticsearch, and GenAI. You are expected to work as an agentic engineer—using AI coding tools and autonomous agents to write code, automate workflows, and optimize how the team delivers. You will collaborate with global teams across multiple time zones and own features end to end. 

In this role, you will:  

  • Bring senior-level Python and LLM engineering expertise to the team 

  • Develop and maintain scalable applications using Python and Java  

  • Design and implement RAG-based solutions using LLMs and vector search  

  • Build and optimize search and retrieval systems using Elasticsearch  

  • Develop document ingestion, indexing, embedding, and retrieval pipelines 

  • Integrate GenAI frameworks and APIs into enterprise applications 

  • Execute both planning and hands-on technical work independently 

  • Collaborate effectively with Product Owners and other stakeholders to solve complex problems 

  • Work cross-functionally to deliver impactful solutions across teams. 

  • Continuously develop your technical expertise and stay current with new technologies 

  • Bring curiosity and drive to expand your skills and knowledge 

  • Use a data-driven approach to solve technical challenges and make informed decisions 

  • Apply systems-level thinking that integrates data science and engineering principles 

  • Take full ownership of the features and projects you work on, delivering high-quality solutions independently 

  • Ensure application performance, scalability, and reliability  

Must-Have Skills: 

  • Hands-on experience in developing RAG (Retrieval-Augmented Generation) solutions, integrating LLMs, and implementing enterprise search capabilities 

  • Designing and implementing RAG systems end to end: vector databases, semantic search, retrieval quality, and chunking strategy 

  • Hands-on, daily use of AI-assisted and agentic coding tools (e.g., Claude Code, Cursor, GitHub Copilot, autonomous coding agents) to write and refactor code, automate workflows, and optimize engineering processes 

  • Strong experience with Cloud platforms (AWS/Azure/GCP) and REST APIs 

  • Grounding in NLP and machine learning as they relate to building LLM systems 

  • Strong experience working with key LLM models APIs (e.g. OpenAI, Anthropic) 

  • Experience building, deploying, and securing MCP servers at scale 

  • Understanding of multi-agent systems and their applications in complex problem-solving scenarios 

  • Experience with distributed search and indexing technologies (e.g., Elasticsearch, OpenSearch, Solr) 

  • Experience with prompt writing for various use cases 

  • Experience with Java or confidence in agentic coding skills to develop in Java  

  • Experience with generative solutions released to prod, at scale, beyond POCs 

  • Proficiency with server-side events, event-driven architectures, and messaging systems 

  • Strong critical thinking and systems thinking skills, with experience debugging, optimizing, and making sound engineering decisions across complex backend systems, not just solving isolated problems. 

  • Solid understanding of security best practices for backend systems, including authentication and data protection 

  • Knowledge of embeddings, vector search, semantic search, and prompt engineering 

  • Familiarty with frameworks such as LangChain, LlamaIndex, or similar  

Other Qualifications: 

  • 2+ years of experience developing and experimenting with LLMs 

  • 8+ years of software development experience  

  • Experience with vector database (Pinecone, FAISS, Waviate, Elasticsearch Vector Search) 

  • Understanding of NLP, LLM Evaluation, and AI application deployment  

Nice-to-Have Skills: 

  • Experience with LLM guardrails 

  • Experience with LLM Frameworks (e.g. LangChain, LlamaIndex) 

  • Experience with LLM monitoring and observability 

  • Experience developing AI/ML technologies within large and business critical applications 

  • Building evaluation into LLM systems: eval harnesses, regression suites, LLM-as-judge, and offline/online quality metrics