Ai Engineer – Generative Ai / Llms / Rag

Halfspace ApS

Remote
Remote
Generative ai
Large language models (llms)
Retrieval-augmented generation (rag)
Halfspace ApS is seeking an AI Engineer with expertise in Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) systems to design and build intelligent applications. The position is remote and emphasizes a blend of software engineering, machine learning, and prompt engineering to deliver scalable AI solutions

Job Summary

  • Design and implement AI-powered applications using LLMs (OpenAI, Anthropic, open-source models, etc.).
  • Build and optimize RAG pipelines (vector databases, embeddings, retrieval strategies).
  • Deploy and monitor AI services in cloud environments (AWS, Azure, GCP).

Matching Summary

Match Score: 85

Halfspace ApS is seeking an AI Engineer with expertise in Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) systems to design and build intelligent applications. The position is remote and emphasizes a blend of software engineering, machine learning, and prompt engineering to deliver scalable AI solutions.

Skills & Requirements

Must-have

  • Generative AI
  • Large Language Models (LLMs)
  • Retrieval-Augmented Generation (RAG)
  • Python programming
  • LLM frameworks (LangChain, LlamaIndex)
  • Vector databases (Pinecone, Weaviate, FAISS)
  • API integration

Nice-to-have

  • Fine-tuning LLMs
  • Transformers and NLP fundamentals
  • Agent-based systems
  • ML Ops / LLM Ops practices
  • Multi-modal models
  • Knowledge graphs

Key Requirements

  • Strong programming skills in Python
  • Experience with LLMs and GenAI frameworks
  • Solid understanding of RAG architectures and embeddings
  • Experience building APIs and scalable backend systems
  • Familiarity with prompt engineering and evaluation techniques
  • Understanding of vector search and semantic retrieval
  • Experience with cloud platforms

Work Rights

Not specified

Tailored Resume

Cover Letter