LLM engineer at Master-Works

Riyadh, Riyadh Region, Saudi Arabia -

Full Time

Start Date

Immediate

Expiry Date

16 May, 26

Salary

0.0

Posted On

15 Feb, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

LLMs, Natural Language Search, Semantic Search, Generative AI, Vector Databases, RAG Pipelines, NL-to-SQL, Embeddings, Python, LangChain, HuggingFace, PyTorch, TensorFlow, Data Pipelines, Prompt Engineering, Fine-Tuning

Industry

IT Services and IT Consulting

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.

Responsibilities

The engineer will design and implement natural language search, semantic search solutions, and generative AI features for analytics web applications, working hands-on with advanced language models and RAG pipelines. Key tasks include developing NL-to-SQL capabilities, building intelligent workflows, creating data embeddings, and optimizing LLM performance for real-world analytics use cases.