Design, develop, and deploy scalable AI solutions leveraging LLMs, Retrieval-Augmented Generation (RAG), and prompt engineering techniques to power intelligent products and services
Job Summary
Design, develop, and deploy scalable AI solutions leveraging LLMs, Retrieval-Augmented Generation (RAG), and prompt engineering techniques to power intelligent products and services.
Own the full lifecycle of model development — from data preparation and fine-tuning to inference optimization and deployment in production environments.
Collaborate with cross-functional teams to identify and implement AI-driven solutions to business problems.
Matching Summary
Design, develop, and deploy scalable AI solutions leveraging LLMs, Retrieval-Augmented Generation (RAG), and prompt engineering techniques to power intelligent products and services.
Skills & Requirements
Must-have
Natural Language Understanding (NLU)
Large Language Models (LLMs)
Retrieval-Augmented Generation (RAG)
Prompt engineering techniques
Python and PyTorch
Transformer architectures
Nice-to-have
Vector databases
LLM fine-tuning
LLM orchestration frameworks
MLOps for LLMs
Embedding models
Key Requirements
8+ years of hands-on experience in NLU
Proven experience developing and deploying NLP or LLM pipelines in production at scale
Proficiency in using LLM provider APIs
Experience with model optimization techniques
Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or related field