Engineering Lead

‒         Design and build AI solutions across a range of business problems, choosing the right approach for each: document and image extraction or classification, predictive models, workflow automation, LLM-based agents and more.

‒         Apply AI engineering best practices across every project: prompt design, retrieval strategies, evaluation frameworks, regression testing and version control for models and prompts.

‒         Set and enforce model governance standards: approval workflows, risk and bias assessment, and documentation for every model promoted to production.

‒         Build observability into every AI system: logging, tracing and monitoring for inputs, outputs, latency and failure modes, so issues surface before they reach the business.

‒         Own token economics and compute cost across LLM-based and other AI systems: track cost per request, choose the right model size for each task, and balance accuracy against spend.

‒         Build and maintain a dashboard that tracks the metrics that matter, such as accuracy, latency, cost, throughput, drift and error rate, across every AI system in production.

‒         Evaluate and select the right AI approach for each problem, whether that is an LLM, a classical machine learning model, computer vision or a mix, based on what the problem actually needs rather than what is fashionable.

‒         Mentor engineers on AI engineering practices, and build a shared standard for how the team designs, tests and ships AI systems.

‒         Explain what an AI system can and cannot do, in plain terms, to non-technical stakeholders and leadership, so expectations stay realistic.

‒         Track new AI and machine learning techniques, and test them against real business needs rather than adopting them for their own sake.

‒         Design and build AI solutions across a range of business problems, choosing the right approach for each: document and image extraction or classification, predictive models, workflow automation, LLM-based agents and more.

‒         Apply AI engineering best practices across every project: prompt design, retrieval strategies, evaluation frameworks, regression testing and version control for models and prompts.

‒         Set and enforce model governance standards: approval workflows, risk and bias assessment, and documentation for every model promoted to production.

‒         Build observability into every AI system: logging, tracing and monitoring for inputs, outputs, latency and failure modes, so issues surface before they reach the business.

‒         Own token economics and compute cost across LLM-based and other AI systems: track cost per request, choose the right model size for each task, and balance accuracy against spend.

‒         Build and maintain a dashboard that tracks the metrics that matter, such as accuracy, latency, cost, throughput, drift and error rate, across every AI system in production.

‒         Evaluate and select the right AI approach for each problem, whether that is an LLM, a classical machine learning model, computer vision or a mix, based on what the problem actually needs rather than what is fashionable.

‒         Mentor engineers on AI engineering practices, and build a shared standard for how the team designs, tests and ships AI systems.

‒         Explain what an AI system can and cannot do, in plain terms, to non-technical stakeholders and leadership, so expectations stay realistic.

‒         Track new AI and machine learning techniques, and test them against real business needs rather than adopting them for their own sake.