LLM / RAG Expert - Agentic AI / Startup - #2630120

LLM / RAG Expert - Agentic AI / Startup

We're partnered with a a very ambitious AI startup that is building next-generation intelligent systems designed to automate complex workflows, unlock value from unstructured data, and deploy AI solutions at scale

.
As they continue to grow, they're looking for a LLM / RAG Expert to play a key role in the development of their core AI platform. This is an opportunity to work on cutting-edge Generative AI products, helping to shape both the technical direction and future capabilities of a rapidly evolving busines

s.
This is a hybrid role based in Frankfurt. Fully remote is not an option right now, sor

ry!
The r

ole:You'll be responsible for designing, developing and deploying production-grade AI systems powered by Large Language Models, Retrieval-Augmented Generation (RAG) architectures, vector search technologies and AI age

nts.Working closely with Product, Engineering and Leadership teams, you'll tackle complex real-world AI challenges whilst helping establish best practices across scalability, performance, observability and secur

ity.
Key responsibili

• ties:Design and develop scalable AI applications powered by
• LLMsBuild and optimise Retrieval-Augmented Generation (RAG) pipe
• linesDevelop semantic search capabilities and vector database solu
• tionsImplement prompt engineering, agent frameworks and tool-calling work
• flowsBuild data ingestion and embedding pipelines across structured and unstructured dat
• asetsImprove model accuracy, retrieval quality, latency and evaluation proc
• essesDeploy, monitor and maintain AI systems in cloud environ
• mentsCollaborate with cross-functional teams to deliver AI-driven product fea
• turesHelp define standards around AI governance, security and observab

ility
What we're looking

• for: 4+ years of software engineering expe
• rience2+ years working with LLMs, Generative AI or NLP applic
• ationsStrong Python development expe
• rienceHands-on experience building production RAG s
• ystemsExperience with vector databases such as Pinecone, Weaviate, Qdrant, Chroma or
• FAISSExperience with frameworks including LangChain, LlamaIndex, Haystack o
• r DSPyStrong understanding of embeddings, chunking strategies, retrieval optimisation and prompt engin
• eeringExperience integrating AI models from providers such as OpenAI, Anthropic, Cohere or Google
• GeminiFamiliarity with cloud platforms including AWS, GCP or
• AzureExperience with Docker, Kubernetes, CI/CD pipelines and modern backend archite

ctures
Desirable expe

• rience:Fine-tuning open-source models such as Llama, Mistral, DeepSeek or
• MixtralAI Agents and multi-agent orches
• trationGraph RAG and knowledge graph implemen
• tationsMultimodal AI
• systemsLLM evaluation and observability
• toolingPrevious experience within startup or scale-up envir
• onmentsOpen-source contributions or technical publi

cations
W

• hy join?Work on genuinely innovative AI products at the forefront of the
• industryHigh levels of ownership and technical
• autonomyInfluence product strategy and technical decisio
• n-makingFast-paced and collaborative env
• ironmentCompetitive salary and equity
• packageFlexible hybrid worki
• ng modelLong-term career growth within a rapidly expanding AI

business
If this sounds interesting and you'd like to learn more, click the link below to apply or email me with a copy of your CV on smouland@eu-rec

ruit.com By applying to this role you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice (https://eu-recruit.com/about-us/privacy