EPI Company
AI LLM Engineer - Remote-First Product & Engineering & Experience · Multiple loc
EPI Company, Germantown, Ohio, United States
Overview
AI LLM Engineer – Remote-First Locations: Remote-First in Belgium, France, Germany, Netherlands, Spain; Fully Remote. What’s in it for you
We are currently on the lookout for an
AI LLM Engineer
with strong hands-on expertise in large language models and retrieval-augmented generation. You will be a key member of the team, responsible for evaluating cutting-edge generative AI tools, designing and benchmarking RAG systems, and experimenting with advanced prompting techniques. Beyond building pipelines, you will play a central role in shaping how we ground AI outputs in factual, reliable data, ensuring our solutions are not only powerful but also trustworthy and user-friendly. Your impact
Evaluate and benchmark LLMs and RAG systems
using metrics such as accuracy, relevance, latency, and hallucination rate Test and compare LLM-based tools
across tasks like summarization, code generation, and Q&A Design and implement end-to-end RAG pipelines , selecting appropriate models, vector stores, and retrieval strategies Build and optimize
semantic search and embedding workflows to ensure scalable, low-latency retrieval Experiment with prompting strategies
(few-shot, chain-of-thought, role-based) to improve coherence and factuality Collaborate with cross-functional teams to
integrate GenAI solutions into workflows
and enhance user experience Stay ahead of trends
in LLMs, RAG, and GenAI agents by testing emerging libraries, APIs, and platforms Technology stack
Languages & frameworks : Python, PySpark, Numpy, Pandas, TensorFlow RAG frameworks : LangChain, LlamaIndex, Haystack, Guidance, PromptLayer LLM & GenAI platforms : Hugging Face Transformers, OpenAI API, Anthropic Claude, Mistral Generative AI tools : Microsoft Copilot, GitHub Copilot, Atlassian Rovo Infrastructure & deployment : AWS, Docker, Kubernetes To succeed, you should meet at least 70% of these requirements
3 to 5 years experience
working as a AI Engineer with
2 to 3 years experience
on
LLM-based applications , including
RAG systems
in real-world use cases Strong understanding of how
GenAI agents
for information retrieval
work Ability to
design and apply evaluation metrics for LLM performance
(accuracy, relevance, hallucination rate, latency) Hands-on experience with RAG frameworks
such as LangChain, LlamaIndex, or Haystack Fluent in English (CEFR C1 or C2) is mandatory; proficiency in German, Dutch, French, or any additional European languages is a plus Recruitment steps
A first call with one of our recruiters An interview focused on the mission and your expertise with your future manager A final interview with one of CPTO Hopefully, an offer you can’t refuse Turn back if …
You’ve used LLMs or GenAI tools in the past, but never looked under the hood You expect fully predefined processes and frameworks instead of experimenting and iterating in ambiguous situations You have never heard of LLM grounding issues and how to solve them. You prefer working only with out-of-the-box solutions rather than designing and fine-tuning your own Otherwise apply!
Equality & Opportunity
Our commitment to equal employment opportunities: EPI offers the same job opportunities to all, without distinction of gender, ethnicity, religion, sexual orientation, social status, disability or age. EPI promotes the development of an inclusive work environment that mirrors the diversity of the clients our product is serving. Locational details
Department: Product & Engineering & Experience Locations: Remote-First in Belgium, France, Germany, Netherlands, Spain Remote status: Fully Remote
#J-18808-Ljbffr
AI LLM Engineer – Remote-First Locations: Remote-First in Belgium, France, Germany, Netherlands, Spain; Fully Remote. What’s in it for you
We are currently on the lookout for an
AI LLM Engineer
with strong hands-on expertise in large language models and retrieval-augmented generation. You will be a key member of the team, responsible for evaluating cutting-edge generative AI tools, designing and benchmarking RAG systems, and experimenting with advanced prompting techniques. Beyond building pipelines, you will play a central role in shaping how we ground AI outputs in factual, reliable data, ensuring our solutions are not only powerful but also trustworthy and user-friendly. Your impact
Evaluate and benchmark LLMs and RAG systems
using metrics such as accuracy, relevance, latency, and hallucination rate Test and compare LLM-based tools
across tasks like summarization, code generation, and Q&A Design and implement end-to-end RAG pipelines , selecting appropriate models, vector stores, and retrieval strategies Build and optimize
semantic search and embedding workflows to ensure scalable, low-latency retrieval Experiment with prompting strategies
(few-shot, chain-of-thought, role-based) to improve coherence and factuality Collaborate with cross-functional teams to
integrate GenAI solutions into workflows
and enhance user experience Stay ahead of trends
in LLMs, RAG, and GenAI agents by testing emerging libraries, APIs, and platforms Technology stack
Languages & frameworks : Python, PySpark, Numpy, Pandas, TensorFlow RAG frameworks : LangChain, LlamaIndex, Haystack, Guidance, PromptLayer LLM & GenAI platforms : Hugging Face Transformers, OpenAI API, Anthropic Claude, Mistral Generative AI tools : Microsoft Copilot, GitHub Copilot, Atlassian Rovo Infrastructure & deployment : AWS, Docker, Kubernetes To succeed, you should meet at least 70% of these requirements
3 to 5 years experience
working as a AI Engineer with
2 to 3 years experience
on
LLM-based applications , including
RAG systems
in real-world use cases Strong understanding of how
GenAI agents
for information retrieval
work Ability to
design and apply evaluation metrics for LLM performance
(accuracy, relevance, hallucination rate, latency) Hands-on experience with RAG frameworks
such as LangChain, LlamaIndex, or Haystack Fluent in English (CEFR C1 or C2) is mandatory; proficiency in German, Dutch, French, or any additional European languages is a plus Recruitment steps
A first call with one of our recruiters An interview focused on the mission and your expertise with your future manager A final interview with one of CPTO Hopefully, an offer you can’t refuse Turn back if …
You’ve used LLMs or GenAI tools in the past, but never looked under the hood You expect fully predefined processes and frameworks instead of experimenting and iterating in ambiguous situations You have never heard of LLM grounding issues and how to solve them. You prefer working only with out-of-the-box solutions rather than designing and fine-tuning your own Otherwise apply!
Equality & Opportunity
Our commitment to equal employment opportunities: EPI offers the same job opportunities to all, without distinction of gender, ethnicity, religion, sexual orientation, social status, disability or age. EPI promotes the development of an inclusive work environment that mirrors the diversity of the clients our product is serving. Locational details
Department: Product & Engineering & Experience Locations: Remote-First in Belgium, France, Germany, Netherlands, Spain Remote status: Fully Remote
#J-18808-Ljbffr