21 hours ago
Remote, Saudi ArabiaStaff+
Responsibilities
- Own the AI architecture and engineering harness, including model selection, prompting patterns, retrieval design, guardrails, and voice pipelines.
- Define evaluation standards, build evaluation and regression systems, and ensure monitoring and online evaluations detect quality, hallucination, and latency issues.
- Lead and mentor a team of AI engineers, conduct design reviews, establish engineering standards, and contribute to hiring.
- Write production code, lead critical AI incident debugging, and manage prototypes validating new models, agent patterns, and voice features.
- Partner with Product and Engineering on customer requirements, tool calling, workflows, deployment, and scaling.
Requirements
- 7+ years of experience in software or ML engineering, including 2+ years building LLM-based applications in production.
- Experience leading at least three AI engineers or scientists technically through design reviews, standards, and mentoring.
- Deep hands-on experience with prompting, structured outputs, guardrails, agent patterns, and harness development.
- Experience building LLM evaluation pipelines using golden datasets, LLM-as-judge methods, and regression suites to gate releases.
- Strong Python skills and experience with APIs, cloud deployment, observability, and debugging distributed systems.
- Fluent written and spoken English with the ability to produce clear design documents and decision records.
- Preferred experience with Arabic or Gulf Arabic NLP, ASR, TTS, real-time voice agents, LLM tracing and online evaluation tools, or fine-tuning and distilling open-weight models.
Benefits
- Remote workplace arrangement.
- Full-time position based in Riyadh, Saudi Arabia.
Tech Stack
Categories
