Senior LLM / Generative AI Engineer

We are looking for a Senior LLM / Generative AI Engineer to own the end-to-end engineering of production-grade Large Language Model (LLM) solutions. The role will cover model selection, prompt engineering, RAG, fine-tuning, AI agents, deployment, LLMOps, evaluation, security, performance optimization, and ongoing production operations.

The ideal candidate should have strong hands-on experience building and deploying LLM-powered enterprise applications and should be comfortable working across AI engineering, cloud/GPU infrastructure, DevOps, security, and system architecture.

Key Responsibilities

• Evaluate and select commercial and open-source LLMs based on accuracy, latency, context length, cost, licensing, data residency, and governance requirements.
• Design and implement prompt engineering strategies, few-shot prompting, structured outputs, function/tool calling, and context management.
• Build production-grade RAG pipelines, semantic search, document understanding, summarization, embeddings, chunking, metadata extraction, and vector search.
• Implement LLM customization using LoRA, QLoRA, PEFT, and fine-tuning where required.
• Build agentic and multi-agent workflows with tool/API integration, memory, state management, and human approval mechanisms.
• Deploy and operate LLM inference platforms across cloud, hybrid, and GPU environments.
• Work with technologies such as vLLM, TensorRT-LLM, TGI, or equivalent inference/serving frameworks.
• Optimize inference using quantization, batching, KV-cache management, speculative decoding, and prompt caching.
• Implement LLMOps practices including model/prompt versioning, deployment pipelines, rollback, canary releases, and A/B testing.
• Develop automated LLM evaluation frameworks, regression testing, hallucination/groundedness checks, and LLM-as-a-judge workflows.
• Implement observability covering latency, TTFT, tokens/second, token usage, failures, refusals, quality regression, and model drift.
• Optimize LLM infrastructure and operational costs through model routing, caching, right-sizing, and capacity planning.
• Implement AI security controls covering prompt injection, data leakage, PII protection, insecure tool use, and adversarial inputs.
• Apply responsible AI, privacy, governance, auditability, and human-in-the-loop principles.
• Mentor engineers and contribute to architecture reviews, technical standards, documentation, and internal training.
• Collaborate with product, data, security, infrastructure, and business teams to deliver enterprise AI solutions.

Required Skills & Experience

• 7–12+ years of experience in software engineering, AI/ML, or related fields.
• Strong hands-on experience with LLMs and Generative AI.
• Strong Python programming and API/microservices development experience.
• Experience with RAG, embeddings, vector databases, semantic search, and LLM applications.
• Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar frameworks.
• Experience with LLM fine-tuning and LoRA/QLoRA/PEFT.
• Experience with LLM inference and serving technologies such as vLLM, TensorRT-LLM, TGI, or equivalent.
• Strong understanding of Docker, Kubernetes, CI/CD, Git, and cloud environments.
• Experience with AWS, Azure, or GCP and GPU-based infrastructure.
• Experience with vector databases such as Pinecone, Milvus, Qdrant, Weaviate, pgvector, Elasticsearch/OpenSearch, or equivalent.
• Understanding of LLM evaluation, monitoring, observability, and LLMOps/MLOps.
• Strong understanding of AI security risks, including prompt injection, data leakage, and insecure tool calling.
• Excellent problem-solving, architecture, communication, and technical leadership skills.

Preferred Experience

• Experience with open-source models such as Llama, Mistral, Qwen, or equivalent.
• Experience with MLflow, Weights & Biases, LangSmith, RAGAS, DeepEval, promptfoo, or similar tools.
• Experience with GPU optimization and inference performance tuning.
• Knowledge of OWASP Top 10 for LLM Applications.
• Experience working with enterprise AI governance, privacy, and responsible AI frameworks.

What We Are Looking For

We are looking for someone who can take an LLM solution from:

Model Selection → Prompt/RAG → Fine-Tuning → Evaluation → Agent/API Integration → Deployment → Monitoring → Optimization → Production Operations

Candidates with strong hands-on production LLM engineering experience will be preferred over candidates whose experience is limited to basic ChatGPT/API integrations or proof-of-concept chatbot development.

Interested candidates can apply with their updated CV highlighting relevant LLM/Generative AI projects and production experience.

Pay: AED12,000.00 - AED15,000.00 per month

Application Question(s):

• Do you have hands-on production experience with LLM/Generative AI systems?
• Do you have hands-on experience building and deploying RAG (Retrieval-Augmented Generation) solutions?

Experience:

• hands-on experience do you have with LLM/Generative AI: 4 years (Required)

Location:

• Dubai (Preferred)

Willingness to travel:

• 100% (Preferred)

Work Location: In person