AI Tech Lead

• Own and be accountable for the AI architecture and harness, including model selection, prompting patterns, retrieval design, guardrails, and voice pipeline
• Make and document technical decisions with clear rationale
• Define the evaluation standard and move key work from experimentation to production
• Introduce leading testing frameworks for Agentic development
• Ensure production monitoring and online evaluations catch quality drops, hallucinations, and latency spikes before customers report them
• Lead the AI team in designing, developing, and delivering Lucidya's Agentic Platform
• Mentor AI engineers, raise the technical bar through pairing and feedback, and contribute to hiring
• Lead debugging of critical production incidents involving AI behavior
• Manage prototypes and experiments to validate new models, agent patterns, and voice features
• Work with Product to turn customer use cases into technical requirements
• Work with Engineering on shared platform work including tool calling, workflows, deployment, and scaling

• 7+ years in software or ML engineering, including 2+ years building LLM-based applications in production
• AI platform-level experience, not just AI point solutions
• Technical leadership of a team of 3+ AI engineers/scientists, including design reviews, standards, and mentoring
• Deep hands-on experience with prompting, structured outputs, guardrails, agent patterns, and harness development (planning, tool use, multi-step reasoning)
• Ability to work in ambiguous settings and bring clarity and structure to complex situations
• Experience building LLM evaluation pipelines, including golden datasets, LLM-as-judge, and regression suites, and using them to gate releases
• Strong Python
• Experience with APIs, cloud deployment, observability, and debugging distributed systems
• Fluent written and spoken English
• Ability to write clear design docs and decision records
• Nice to have: Arabic NLP experience, especially Gulf Arabic, in LLM or speech systems
• Nice to have: Voice AI experience with ASR, TTS, real-time voice agents, and latency optimization
• Nice to have: Hands-on use of LLM tracing and online evaluation tools such as Langfuse, Arize, or similar
• Nice to have: Fine-tuning or distilling open-weight models and serving them cost-effectively