AI Tech Lead

Job Summary

The AI Tech Lead is a senior engineer responsible for the quality, reliability, and technical direction of the AI layer in Lucidya’s agentic platform. This role involves both hands-on coding and leadership of an AI engineering team.

Responsibilities

• Own the AI architecture including model selection, prompting, retrieval design, guardrails, and voice pipeline.
• Document technical decisions with clear explanations.
• Define evaluation standards and transition key work from experimentation to production.
• Implement testing frameworks and ensure production monitoring detects quality issues early.
• Lead the AI team in designing and delivering the Agentic Platform.
• Mentor AI engineers, provide feedback, and participate in hiring.
• Lead debugging of critical AI production incidents.
• Manage prototyping and experiments to validate new AI capabilities before team adoption.
• Collaborate with Product to translate customer use cases into technical requirements.
• Work with Engineering on shared platform aspects like tool calling, workflows, deployment, and scaling.

Must haves

• 7+ years in software or ML engineering, including 2+ years building LLM-based applications in production.
• Technical leadership experience managing a team of 3+ AI engineers/scientists.
• Deep hands-on experience with LLM application engineering: prompting, structured outputs, guardrails, agent patterns.
• Ability to clarify and structure ambiguous situations.
• Experience building LLM evaluation pipelines and gating releases.
• Strong Python skills and experience with APIs, cloud deployment, observability, and debugging distributed systems.
• Fluent written and spoken English with ability to write clear design documents and decision records.

Nice to haves

• Experience with Arabic NLP, especially Gulf Arabic, in LLM or speech systems.
• Experience with Voice AI including ASR, TTS, real-time voice agents, and latency optimization.
• Hands-on use of production monitoring tools for LLMs such as Langfuse or Arize.
• Experience with model adaptation like fine-tuning or distilling open-weight models and cost-effective serving.

We refresh listings regularly, but some roles close early on the source platform.