AI Tech Lead

This is a fully remote position, open to applicants in Saudi Arabia.

📋 Description

• Take ownership and responsibility for the AI architecture and harness, which encompasses model selection, prompting frameworks, retrieval design, guardrails, and the voice pipeline.

• Make and document technical choices with a well-defined rationale.

• Establish the evaluation criteria and transition significant work from experimentation to production.

• Implement leading testing frameworks to support Agentic development.

• Ensure that production monitoring and online assessments identify quality declines, hallucinations, and latency spikes before they are flagged by customers.

• Guide the AI team in the design, development, and delivery of Lucidya's Agentic Platform.

• Mentor AI engineers, elevate the technical standards through collaboration and feedback, and assist in the hiring process.

• Oversee the debugging of critical production incidents related to AI behavior.

• Manage prototypes and experiments to validate new models, agent patterns, and voice functionalities.

• Collaborate with Product to convert customer use cases into technical specifications.

• Work alongside Engineering on shared platform initiatives including tool integration, workflows, deployment, and scalability.

⛳️ Requirements

• Over 7 years of experience in software or ML engineering, with at least 2 years dedicated to developing LLM-based applications in a production environment.

• Experience at the AI platform level, rather than just implementing AI point solutions.

• Technical leadership experience managing a team of 3 or more AI engineers/scientists, including conducting design reviews, setting standards, and providing mentorship.

• Extensive hands-on experience with prompting, structured outputs, guardrails, agent patterns, and harness development (including planning, tool utilization, and multi-step reasoning).

• Capacity to work in ambiguous environments and provide clarity and organization to complex situations.

• Experience in constructing LLM evaluation pipelines, including golden datasets, LLM-as-judge, and regression suites, as well as using these to regulate releases.

• Proficient in Python.

• Familiarity with APIs, cloud deployment, observability, and debugging of distributed systems.

• Fluent in both written and spoken English.

• Ability to produce clear design documents and decision records.

• Preferred: Experience in Arabic NLP, particularly Gulf Arabic, within LLM or speech systems.

• Preferred: Experience in Voice AI involving ASR, TTS, real-time voice agents, and latency optimization.

• Preferred: Practical use of LLM tracing and online evaluation tools such as Langfuse, Arize, or comparable tools.

• Preferred: Experience in fine-tuning or distilling open-weight models while serving them in a cost-effective manner.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health insurance coverage.

• Opportunities for professional development and continuous learning.

• Flexible working hours and remote work options.

• A dynamic and inclusive work environment that fosters collaboration and innovation.