emagine | 10 days ago | Remote

Main Responsibilities

Build and deploy GraphRAG solutions integrating knowledge graphs (e.g., Neo4j) and vector databases (e.g., Weaviate).
Develop Hybrid Retrieval systems using FAISS/Milvus + BM25.
Fine-tune LLMs (GPT, LLaMA, Falcon) using LoRA/PEFT.
Build scalable GenAI pipelines using Hugging Face, LangChain, Weaviate, and OpenAI APIs.
Implement Weaviate’s Ignition Framework for enterprise-grade RAG (mandatory).
Deploy solutions on AWS/GCP/Azure with strong MLOps practices.
Evaluate and optimize retrieval and generation performance.
Work closely with engineering and product teams to deliver production AI systems.
Maintain strong documentation, monitoring, and optimization of AI pipelines.

Key Requirements

5–8+ years of hands-on AI/ML engineering with production deployments.
Strong NLP + LLM experience:
- LoRA/PEFT fine-tuning
- Prompt engineering
- Embeddings & retrieval optimization
Practical experience with GraphRAG, knowledge graphs, and Neo4j.
Mandatory: Experience with Weaviate’s Ignition Framework.
Strong Python; PyTorch/TensorFlow proficiency.
Experience with Hybrid Retrieval (FAISS, Milvus, Pinecone + BM25).
Solid knowledge of vector databases and RAG pipelines.
Real GenAI product experience (not academic).
Strong English communication; ability to work with partial Poland timezone coverage

Official notification