Senior LLM / AI Engineer📣 إعلان

About the Role

Ninja is seeking a Senior LLM / AI Engineer to join its team in Riyadh. This full-time role is central to establishing Ninja's AI function. While the position is designated Senior, it is open to candidates with 0-1 years of relevant experience who demonstrate exceptional hands-on engineering capability and a strong drive to deliver production-ready AI systems.

Role Overview and Impact

This is a hands-on engineering role focused on designing, developing, and deploying agentic AI systems that achieve real business impact. The successful candidate will work on critical areas such as customer care automation, knowledge management pipelines, and intelligent targeting and decision-making engines. The objective is to ensure scalable, reliable, and high-performance AI solutions, directly shaping the future of AI at Ninja.

Key Responsibilities

• Design, develop, and deploy production-ready agentic AI systems that deliver tangible business impact.
• Contribute to customer care automation, knowledge management pipelines, and intelligent targeting and decision-making engines.
• Ensure the development of scalable, reliable, and high-performance AI solutions.
• Act as a hands-on engineer, prioritizing the shipment of production systems over experimental prototypes.

Required Technical Skills

• Programming & Services: Strong proficiency in Python (*** with production experience in FastAPI services.
• Agentic Workflow Design: Experience designing or building multi-step agentic workflows, understanding tradeoffs between deterministic state machines/graphs and open-ended ReAct-style agents.
• LLM Integration: Direct production experience with Anthropic and/or OpenAI SDKs, comfortable working without heavy abstraction layers. LangGraph experience is a plus.
• Retrieval Judgment: Understanding of when structured/keyed database lookups are superior to vector search, and practical implementation of RAG when appropriate.
• Data Layer: Proficiency with PostgreSQL, SQLAlchemy (async), Alembic migrations, pgvector, and Redis for session/state management.
• Production Discipline: Experience shipping systems with real guardrails, including cost controls, latency budgets, escalation/fallback paths, and evaluation loops. Familiarity with LLM observability tools (*, Langfuse, LangSmith, Helicone) is expected.
• Prompt Engineering & Evals: Practical experience writing, testing, and iterating on prompts, including building or utilizing eval frameworks to prevent regressions.

Candidate Profile and Desired Attributes

• MCP / Tool-Serving: Exposure to MCP (Model Context Protocol) servers or similar tool-exposure patterns for AI assistants is a strong plus.
• Multilingual Capabilities: Experience with Arabic or other non-English LLM applications, including dialect handling and multilingual evaluations, is a nice-to-have.
• Public GitHub: A public GitHub profile showcasing real, browsable work (personal projects, open-source contributions, or code samples) is required.
• Hands-on Builder: Demonstrated ability as a genuine hands-on builder, capable of walking through personally written code line-by-line, explaining decisions and lessons learned.
• Ownership and Proactivity: Ability to identify problems and drive solutions independently, with minimal oversight, in a founding role.

Work Location

This full-time position is based in Riyadh, Saudi Arabia.