Solution Design & Build: Use UnifyApps no-code builder to create AI agents and GenAI apps using Application, Automation, Data, and AI Agent modules
Prompting & RAG: Engineer prompts, tool/function calling, chunking/embedding, vectorization, reranking, grounding, and guardrails for high-quality Arabic/English outputs
Agent Evaluation: Create golden test sets; use agent-eval frameworks to track accuracy
LLM Model training & fine-tuning (via prompt engineering & other methods) in Arabic and English
Customer Delivery: Run discovery, define user stories & acceptance criteria, build PoCs/MVPs, iterate rapidly with stakeholders
Platform Expertise: Become an SME on the UnifyApps platform; provide structured product feedback to influence roadmap
Requirements
Experience: 24 years in AI/LLMs building real applications or agents
Language: Professional Arabic & English (read/write/communicate)
In-depth knowledge on Gen AI: LLMs, team of agents,, MCP/A2A, RAG (chunking, embeddings, reranking, vector DBs), grounding/hallucination, AI governance, auditability, evaluation, HITL etc
Model Ops: Prompt engineering, golden test set creation, agent-eval frameworks, A/B testing, regression analysis, basic fine-tuning (PEFT/LoRA)
Integrations: REST/GraphQL APIs, OAuth, webhooks; stitching systems into end-to-end flows
