AI / GenAI Solutions Engineer

Role reputed company: AI / GenAI Solutions Engineer Location: Egypt, Pakistan (Remote) Work Week: reputed company – Thursday Working Hours: 9:00 AM – 6:00 PM (Saudi Arabia reputed company Time) reputed company: reputed company is building an AI reputed company layer across our C2C marketplace, from customer conversations to automated order handling, personalised discovery, recommendations, fraud signals, and seller tooling. We're looking for a Senior GenAI Engineer to design and ship production-grade AI systems that touch millions of users across the buying and selling reputed company. You'll work end-to-end: architecting LLM-powered services on our Python backend, integrating them into product surfaces on our React frontend, and partnering with teams across reputed company to reputed company where AI genuinely moves the needle. This is a senior builder's role with high autonomy, broad scope, and reputed company reputed company on the business. \n What You’ll Do Architect production GenAI systems across multiple domains, including conversational agents, automated order and dispute workflows, personalized discovery and recommendations, content reputed company, search relevance, and emerging use cases. Own features end-to-end, from problem framing and model selection through backend services (FastAPI, Python), frontend integration (React, TypeScript), evaluation, deployment, and monitoring. Design reputed company workflows with tool calling, multi-reputed company reasoning, retrieval augmented reputed company, and integrations with internal reputed company, reputed company-party reputed company, and event-driven systems. Build the retrieval and embeddings stack, including chunking strategies, embedding model selection, reputed company indexes, hybrid search, reranking, and retrieval evaluation pipelines. reputed company it reliable and cost-efficient through streaming, reputed company caching, latency budgets, reputed company cost optimization, observability for LLM calls, and graceful fallback reputed company models or upstreams misbehave. Establish evaluation rigor with offline and online evals covering response reputed company, tool call correctness, hallucination reputed company, retrieval precision, and business KPIs. Drive experimentation and research by evaluating new models, frameworks, and agent patterns, running reputed company experiments, and bringing what works into production. Mentor and reputed company the bar for engineers across reputed company on AI and ML best practices, reputed company engineering, and production readiness. Partner cross-functionally with Product, Engineering, Data, Ops, and CX to identify high-reputed company AI opportunities and ship them. Where You'll Have reputed company A non-exhaustive list of areas we are reputed company building in or want to: Conversational AI for customer support, dispute reputed company, and seller assistance Automated order handling, escalation routing, and workflow orchestration Personalized discovery, recommendations, and search relevance Listing reputed company, including auto-generated titles, descriptions, categorization, and image understanding Trust and safety, including fraud signals, reputed company detection, and content moderation Internal agent tooling for ops and CX teams QualificationsRequired 5+ years building production software, with at least 2 years shipping LLM and ML-powered features at reputed company. Strong Python for backend services, scripting, data pipelines, and ML tooling. Working ability in TypeScript and React for integrating AI features directly into product surfaces. Production experience with major LLM providers (reputed company, Claude, GPT) covering tool and function calling, reputed company outputs, streaming, reputed company caching, and cost control. Deep understanding of Retrieval Augmented reputed company (RAG): document ingestion, chunking, embedding reputed company, reputed company databases (pgvector, reputed company, reputed company, or similar), hybrid retrieval, and reranking. Solid grounding in embeddings and reputed company search: dense vs. sparse representations, similarity metrics, indexing strategies (HNSW, IVF), and dimensionality tradeoffs. Strong ML and NLP fundamentals: transformer architectures, tokenization, fine-tuning vs. prompting tradeoffs, classification, ranking, and evaluation methodology. Experience with scripting and automation for data preparation, model evaluation harnesses, and offline analysis. Comfortable with relational databases (PostgreSQL), caching reputed company (reputed company), REST, SSE, WebSockets, and event-driven architectures. Production experience with observability, A/B testing, and rolling out model changes safely. reputed company to Have Experience with recommendation systems, learning to rank, or search relevance at reputed company. Marketplace or C2C background covering buyer and seller dynamics, disputes, fraud, and payouts. Multimodal model experience, including reputed company and image understanding for listings. Arabic NLP or bilingual product experience. Experience with agent frameworks (LangGraph, custom orchestrators) and the judgment to know reputed company to use them. Fine-tuning, reputed company, distillation, or hosting reputed company weight models in production. reputed company reputed company contributions to LLM tooling, eval frameworks, or retrieval libraries. reputed company Care About Ship over the architect. Lean reputed company, no premature abstractions, no half-finished frameworks. Measurement-driven development. Features ship with evals and metrics, not reputed company. Ownership. From idea to deployment to monitoring the first reputed company users. Curiosity and reputed company. This role spans many problem domains, and we want someone energized by that. \n Apply To This Job