LLM engineer

Masterworksco

Apply to this job
Riyadh, Riyadh Province, Saudi Arabia on site Until 8/23/2026 First posted February 15, 2026 Last posted February 15, 2026
Job description

About the Role: 

Master works is looking for an experienced LLM Engineer to join our team working on next-generation AI-driven analytics solutions. The ideal candidate will design and implement natural language search, semantic search solutions, and generative AI features for our web applications. You will work hands-on with advanced language models, vector databases, RAG pipelines, and build intelligent workflows to enable actionable insights from both structured and unstructured data. 

Key Responsibilities: 

  • Develop and maintain natural language search capabilities and semantic search solutions using vector databases. 
  • Implement NL-to-SQL pipelines and other intelligent query generation features for analytics platforms. 
  • Build and optimize Generative AI features (summarization, recommendations, insights) for analytics applications. 
  • Design and implement Agents and Workflows for complex tasks across datasets. 
  • Develop RAG (Retrieval-Augmented Generation) pipelines for knowledge retrieval and query resolution. 
  • Create embeddings for structured and unstructured data and leverage them for semantic understanding and search. 
  • Process and transform structured (tables, CSV, SQL) and unstructured data (text, documents, logs) as input/output for AI models. 
  • Collaborate with data engineers, analysts, and product teams to integrate AI features seamlessly into the platform. 
  • Evaluate, benchmark, and optimize LLM performance for real-world analytics use cases.  

Required Qualifications & Skills: 

  • Bachelor's or master's degree in computer science, AI/ML, Data Science, or related field. 
  • Hands-on experience with LLMs (OpenAI, Anthropic, Cohere, or similar). 
  • Experience with vector databases such as Pinecone, Weaviate, Milvus, or FAISS. 
  • Strong understanding of embeddings, semantic search, and their practical applications. 
  • Expertise in RAG pipelines, Agents, and Workflow orchestration. 
  • Proficiency in Python and relevant AI/ML frameworks (LangChain, HuggingFace, PyTorch, TensorFlow). 
  • Familiarity with NL-to-SQL systems and natural language query processing. 
  • Experience working with structured and unstructured data sources. 
  • Knowledge of data pipelines, preprocessing, and storage formats for analytics. 
  • Ability to design scalable, production-ready AI solutions integrated with web applications. 

Preferred Qualifications: 

  • Experience working with AI based chatbots, Natural language search, NL to SQL. 
  • Knowledge of prompt engineering and fine-tuning LLMs. 
  • Familiarity with data privacy, security, and compliance considerations in AI pipelines. 

Soft Skills: 

  • Strong problem-solving and analytical skills. 
  • Excellent communication skills to work with cross-functional teams. 
  • Passion for AI and staying up to date with the latest developments in LLMs and generative AI. 
About this role

Summary

Develop and optimize AI-driven language search, generative features, and workflows for analytics platforms.

Job title

LLM engineer

Experience level

not specified

Industry

software

Location requirements

Riyadh, onsite; remote not specified

Salary

Not specified

Management role

No

Skills & keywords

Required skills

LLMsPythonvector databasesembeddingsRAG pipelinesNL-to-SQLAI frameworks (LangChain, HuggingFace, PyTorch, TensorFlow)

Preferred skills

chatbotsprompt engineeringLLM fine-tuningdata privacy

Specializations

natural language processingvector databasesgenerative AIRAG pipelinesembeddings
Locations

Structured locations inferred from the posting.

Riyadh Saudi Arabia

On-site City