Lead Gen-AI Engineer

<p>Equal Experts is an innovative consultancy specialising in the delivery of custom software solutions for&nbsp;blue-chip enterprise and public sector clients across a range of industry sectors. We work on important&nbsp;projects for our clients, deliver market-leading propositions across the digital, online and mobile&nbsp;channels, and are recognised for our leadership in the application of agile and lean delivery methods to&nbsp;assure delivery. We have offices in Australia, India, South Africa, the UK, the EU and the USA.</p> <p><br>This role involves working in teams that use modern agile technical practices - including continuous&nbsp;integration and deployment and fast feedback loops - to deliver timely and pragmatic solutions, as well&nbsp;as helping others to do their jobs in a more effective way.</p> <p><br><strong>Responsibilities</strong><br>● As a Gen AI Engineer, you will be responsible for designing, testing, and deploying GenAI&nbsp;solutions that leverage LLMs and related technologies. You’ll work on solutions that incorporate&nbsp;prompt engineering, model evaluation, retrieval-augmented generation (RAG), and continuous&nbsp;performance monitoring, all while adhering to best practices in software engineering. This role&nbsp;blends data science, data engineering, and MLOps expertise, with a focus on making AI&nbsp;solutions reliable and production-ready.</p> <p>Required Skills<br>● Solution Prototyping &amp; Testing: Rapidly test various models and approaches to determine the&nbsp;best fit for the project without extensive over-investment. Stay updated on LLM advancements&nbsp;(e.g., GPT-3.5 to GPT-4).<br>● Prompt Engineering: Write, test, and refine prompts, including creating effective prompt chains&nbsp;and managing prompt versions for optimal results.<br>● Model &amp; Prompt Evaluation: Analyze model and prompt performance to ensure reliability.&nbsp;Develop robust testing methodologies, incorporating training and test sets for thorough&nbsp;evaluation.<br>● Performance Monitoring: Build pipelines to monitor model responses and track performance&nbsp;metrics in production for ongoing optimization.<br>● RAG Architecture Implementation: Design and maintain retrieval-augmented generation (RAG)&nbsp;architectures. Work with data pipelines, vector databases, and search algorithms. Manage&nbsp;document chunking and embedding selection for optimal context window usage.<br>● Data Extraction: Extract data from various sources (e.g., PDF files) as part of the RAG process.<br>● Software Development Best Practices: Employ CI/CD, test-driven development, and sound architectural principles in all GenAI solutions.<br>● Evaluation Scripts &amp; Load Testing: Develop tests for the random nature of LLM outputs and&nbsp;conduct load testing to ensure system robustness, even when reliant on third-party APIs.<br>● ETL &amp; Traditional Data Management: Build data pipelines to manage and integrate traditional&nbsp;relational data where necessary.</p>