Lead Gen AI Engineer

The candidate will have responsibilities across the following functions:

GenAI Application Design and Implementation:

• Design, architect, and implement scalable Generative AI applications and infrastructure using LLMs (e. g., OpenAI, Gemini, Llama2 GPT-4), multi-modal models, and open-source frameworks within Azure.
• Develop robust data integration pipelines and RAG workflows using tools like Azure AI Search, Semantic Search, Hybrid Search, Document Intelligence, Skillsets, Generative RAG Search, ADF Pipelines, LangChain, Semantic Kernel, and Promptflow.
• Lead prompt engineering, fine-tuning, and model optimisation for custom business use cases, ensuring performance, accuracy, and ethical compliance through rigorous testing (prompt evaluation, bias detection, hallucination analysis, and benchmarking). Advise and implement a roadmap for infrastructure, GenAI model catalogues, and frameworks aligned with business goals.

System Support and Operational Excellence:

• Support AI developers, data analysts, and data scientists in accessing and interacting with Generative AI solutions, resolving issues related to prompt engineering, accuracy, relevancy, and performance through root cause analysis.
• Monitor system performance, storage capacity, and reliability using tools like Azure Application Insights, identifying opportunities for optimisation and addressing production issues promptly with proper validation and deployment steps.
• Support the development and maintenance of RAG pipelines and LLM-based solutions, ensuring high availability and performance through proactive monitoring and troubleshooting. Deliver clear, professional communication to users, management, and teammates, providing ad hoc data extracts and analysis to meet tactical business needs.

Innovation and Technology Leadership:

• Serve as a role model in continuous improvement by experimenting with emerging technologies and articulating their value to the product organisation.
• Collaborate with Solution Architects to deliver enterprise initiatives such as application security, API design, architecture, and test automation, driving innovation through cutting-edge Generative AI strategies.
• Act as a subject matter expert in tools and technologies, lead internal learning forums, set forum objectives, and promote the adoption of new technologies and methods. Demonstrate deep understanding of the technology and business landscape to solve complex business challenges.

Mentorship and Team Leadership:

• Mentor and coach development staff across functions, fostering a culture of learning, excellence, and cross-functional collaboration.
• Lead design reviews, influence enterprise initiative prioritisation, and guide the team on best practices, test automation strategies, and infrastructure design. Facilitate optimal backlog execution, mentor developers in designing complex business applications, and provide guidance on effective estimation techniques.
• Collaborate with Solution Architects to reduce technical debt and ensure system reliability, performance, and ethical standards in AI systems.

Cross-Functional Collaboration and Technical Excellence:

• Collaborate with Solution Architects to analyse requirements, lead consensus on implementation, and align with enterprise architecture for seamless integration of heterogeneous data.
• Actively participate in peer code reviews, write and integrate automated tests into CI/CD pipelines, and contribute to post-deployment test automation frameworks to improve test efficiency, coverage, and stability.
• Support production deployments with detailed documentation and risk mitigation strategies, ensuring high-quality, secure, and maintainable software.

Requirements:

• Expertise with GenAI tools (Azure AI Search, Semantic Search, Hybrid Search, Document Intelligence, Skillsets, Generative RAG Search, ADF Pipelines, LangChain, Semantic Kernel, Promptflow) *Proficiency in leading LLMs (OpenAI, Gemini, Llama2 GPT-4) and multi-modal models.
• Advanced knowledge of prompt engineering, fine-tuning, and model optimisation
• Experience with RAG workflows, agentic AI frameworks, and ethical AI practices (bias detection, hallucination analysis).
• Strong understanding of CI/CD pipelines, automated testing, and test automation frameworks.
• Exceptional mentorship, leadership, and communication skills.
• Deep knowledge of enterprise architecture, application security, and API design.
• Commitment to driving innovation and adopting emerging technologies.