AI / LLM Engineer

We’re hiring an experienced AI / LLM Engineer for our UK-based client to build and optimise a production-grade, customer-facing AI assistant.

📍 Location: Islamabad
🏢 Work Mode: 100% On-site
🕐 Working Hours: UK Hours (12 PM–9 PM PKT)

Key Responsibilities

• Design and deploy scalable LLM systems for production use.
• Build and optimise RAG pipelines and knowledge retrieval systems.
• Develop embedding pipelines and work with vector databases.
• Implement fine-tuning workflows and model evaluation pipelines.
• Develop AI guardrails, policy enforcement, and escalation mechanisms.
• Optimise model performance, latency, concurrency, and GPU utilisation.
• Ensure AI systems are reliable, observable, and fully auditable.
• Integrate AI solutions with databases, APIs, and existing applications.
• Collaborate with technical, compliance, and legal teams.

Technical Requirements

• Strong production experience with Python and FastAPI or similar frameworks.
• Proven experience building and deploying LLM applications in production.
• Hands-on experience with RAG, embeddings, vector databases, and LLM APIs.
• Experience with prompt engineering, structured outputs, and AI evaluation.
• Experience with Docker, Redis, AWS, APIs, and databases.
• Understanding of LLM performance optimisation, scaling, and concurrency.
• Familiarity with open-source LLMs, vLLM, fine-tuning, or GPU deployment is a plus.