GenAI Engineer

We are looking for a hands-on GenAI Engineer to design, build, and deploy production-grade AI applications powered by Large Language Models (LLMs). This role is focused on turning business use cases into reliable, scalable AI solutions such as copilots, knowledge assistants, document intelligence tools, and workflow automation systems.

The ideal candidate combines strong software engineering skills with practical experience in LLM application development, Retrieval-Augmented Generation (RAG), prompt engineering, model evaluation, and API integration. This person should be comfortable moving from prototype to production while optimizing for quality, latency, security, and cost. This builds on the original JD’s emphasis on LLM apps, RAG, integrations, vector databases, and cloud deployment.

Key Responsibilities:

• Design, develop, and deploy GenAI applications using LLMs for real-world business workflows.
• Build AI-powered solutions such as chatbots, copilots, knowledge assistants, search assistants, and workflow automation tools
• Architect and optimize RAG pipelines using structured and unstructured enterprise data.
• Develop robust prompt strategies, guardrails, and response orchestration for accuracy and safety.
• Integrate AI capabilities into web applications, backend systems, APIs, and enterprise platforms.
• Work with vector databases and retrieval systems to improve relevance and response quality.
• Evaluate model performance using defined quality metrics, test cases, and user feedback loops.
• Improve production performance across latency, cost, scalability, observability, and reliability.
• Collaborate with product, engineering, and business teams to translate use cases into deployable AI features.
• Stay updated with emerging GenAI tools, frameworks, and model capabilities, and recommend practical adoption where relevant.

Must-Have Skills:
Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
Strong hands-on programming experience in Python.
Experience building GenAI applications using frameworks such as LangChain, LlamaIndex, or equivalent orchestration tools.
Experience working with OpenAI APIs, Anthropic, Bedrock, Azure OpenAI, or similar LLM platforms.
Strong understanding of prompt engineering, RAG architecture, and LLM application design.
Experience integrating AI models with REST APIs, web applications, and backend services.
Familiarity with vector databases such as FAISS, Pinecone, Weaviate, Chroma, or similar.
Good understanding of machine learning and NLP fundamentals.

Experience deploying production-ready applications on AWS, Azure, or GCP.

Ability to evaluate and improve model quality, including hallucination reduction and retrieval performance.

Understanding of security, access control, and safe handling of enterprise data in AI applications.

Preferred Skills :
Experience with Amazon Bedrock.
Experience with multimodal AI applications involving text, images, PDFs, and document processing.
Familiarity with fine-tuning, adapters, or domain adaptation techniques for LLMs.

Experience with Docker, Kubernetes, CI/CD pipelines, and MLOps workflows.

Exposure to observability and monitoring tools for AI systems.

Experience building domain-specific assistants for operations, compliance, technical support, or enterprise knowledge systems.

Experience Required:

2–3 years of experience in software engineering, machine learning, or AI application development.

At least 1–2 years of practical experience working on GenAI / LLM-based applications in production or advanced PoCs.

Job Types: Full-time, Permanent

Ability to commute/relocate:

• Abu Dhabi: Reliably commute or planning to relocate before starting work (Required)

Application Question(s):

• What is your Visa Status?
• What is your Current Salary?
• What is your Expected Salary?
• Visa Expiry Date?
• Duration of Notice Period?
• Mention your available dates for an online interview

Experience:

• GenAI: 2 years (Required)

Location:

• Abu Dhabi (Required)

Work Location: In person