Data Engineer / Sciences : RAG NLP LLM
Core
Design, develop, and deploy advanced NLP, RAG, and LLM solutions to power business applications like chatbots and content generation.
Role type
Senior IC Data Engineer / NLP Scientist (RAG & LLM)
Builds
Production-ready AI pipelines, RAG systems, and optimized LLM applications
Domain
Artificial Intelligence, Natural Language Processing, Cloud Infrastructure
Deliverable
production ML models
Required skills
Python, NLP (fine-tuning, classification), RAG architecture, LLM deployment, Data Engineering (ETL/ELT), Vector databases, Cloud platforms (AWS/Azure/GCP), MLOps/DevOps
Preferred skills
TensorFlow, PyTorch, Hugging Face, LangChain, LlamaIndex, Apache Spark, Kubernetes
Technologies
Pinecone, Weaviate, FAISS, Docker, Kubernetes, MLflow, Kafka, PostgreSQL, MongoDB
Responsibilities
Develop and maintain scalable ETL/ELT pipelines for AI data ingestion; Implement and optimize RAG architectures with vector databases; Fine-tune and deploy pre-trained language models for specific use cases; Collaborate with DevOps to containerize and deploy solutions to production; Monitor and evaluate model performance and quality
Seniority
Mid-Senior, hands-on IC