Lucidya | لوسيديا
Lucidya | لوسيديا
Lucidya dezvoltă instrumente de analiză bazate pe inteligență artificială pentru rețelele sociale și platformele online, ajutând companiile să înțeleagă sentimentul clienților, să monitorizeze reputația mărcii și să ia decizii de marketing bine fundamentate. Instrumentele sale sunt adaptate publicului vorbitor de arabă, analizând conversațiile digitale și evidențiind informații utile pentru interacțiunea cu clienții și strategia de marketing.

Senior AI Tech Lead, Remote in Saudi Arabia

Lead the architecture, evaluation, and production delivery of Lucidya’s agentic customer experience platform. Guide AI engineers building dependable Arabic and English agents.

Descriere

  • Own the AI architecture and development framework, covering model selection, prompting, retrieval, safeguards, and voice systems.
  • Record technical decisions and explain the reasoning behind them.
  • Set evaluation standards and bring priority work from experimentation into production.
  • Adopt testing frameworks for agentic development.
  • Use production monitoring and live evaluations to detect quality issues, hallucinations, and latency spikes before customers report them.
  • Lead the AI team in designing, building, and delivering Lucidya’s agentic platform.
  • Mentor AI engineers through pairing and feedback, strengthen technical standards, and contribute to hiring.
  • Lead investigations into critical production incidents involving AI behavior.
  • Oversee prototypes and experiments that assess new models, agent approaches, and voice capabilities.
  • Partner with Product to translate customer use cases into technical requirements.
  • Collaborate with Engineering on shared platform capabilities, including tool calling, workflows, deployment, and scaling.

Cerințe

  • At least 7 years of software or machine learning engineering experience, including 2 or more years building production LLM applications.
  • Experience at the AI platform level, beyond individual AI solutions.
  • Technical leadership of at least 3 AI engineers or scientists, including design reviews, standards, and mentoring.
  • Extensive hands-on work with prompting, structured outputs, safeguards, agent approaches, and development frameworks for planning, tool use, and multi-step reasoning.
  • Ability to bring clarity and structure to complex, ambiguous situations.
  • Experience building LLM evaluation pipelines with golden datasets, LLM-as-judge, and regression suites, and using them to gate releases.
  • Strong Python skills.
  • Experience with APIs, cloud deployment, observability, and debugging distributed systems.
  • Fluent written and spoken English.
  • Ability to write clear design documents and decision records.
  • Preferred: Arabic NLP experience, particularly Gulf Arabic, in LLM or speech systems.
  • Preferred: Voice AI experience with ASR, TTS, real-time voice agents, and latency optimization.
  • Preferred: Hands-on experience with LLM tracing and online evaluation tools such as Langfuse, Arize, or similar.
  • Preferred: Experience fine-tuning or distilling open-weight models and serving them cost-effectively.

Locuri de muncă similare

Nu s-au găsit locuri de muncă

Încercați să ajustați sau să ștergeți filtrele pentru a găsi mai multe oportunități.