AI / GenAI Solutions Engineer

<p><strong>Role Name: AI / GenAI Solutions Engineer</strong></p> <p><strong>Location:</strong> Egypt,  Pakistan (Remote)</p> <p><strong>Work Week:</strong> Sunday – Thursday</p> <p><strong>Working Hours:</strong> 9:00 AM – 6:00 PM (Saudi Arabia Standard Time)</p> <h3><span style="text-decoration: underline;"><strong style="font-size: 11pt;">Overview:</strong></span></h3> <p>Soum is building an AI native 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 journey.</p> <p>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 the company to find where AI genuinely moves the needle. This is a senior builder's role with high autonomy, broad scope, and real impact on the business.</p> <p> </p> <p></p><p><br></p><b>What You’ll Do</b><div> <ul> <li> <p><strong>Architect production GenAI systems</strong> across multiple domains, including conversational agents, automated order and dispute workflows, personalized discovery and recommendations, content generation, search relevance, and emerging use cases.</p> </li> <li> <p><strong>Own features end-to-end</strong>, from problem framing and model selection through backend services (FastAPI, Python), frontend integration (React, TypeScript), evaluation, deployment, and monitoring.</p> </li> <li> <p><strong>Design agentic workflows</strong> with tool calling, multi-step reasoning, retrieval augmented generation, and integrations with internal APIs, third-party SaaS, and event-driven systems.</p> </li> <li> <p><strong>Build the retrieval and embeddings stack</strong>, including chunking strategies, embedding model selection, vector indexes, hybrid search, reranking, and retrieval evaluation pipelines.</p> </li> <li> <p><strong>Make it reliable and cost-efficient</strong> through streaming, prompt caching, latency budgets, token cost optimization, observability for LLM calls, and graceful fallback when models or upstreams misbehave.</p> </li> <li> <p><strong>Establish evaluation rigor</strong> with offline and online evals covering response quality, tool call correctness, hallucination rate, retrieval precision, and business KPIs.</p> </li> <li> <p><strong>Drive experimentation and research</strong> by evaluating new models, frameworks, and agent patterns, running focused experiments, and bringing what works into production.</p> </li> <li> <p><strong>Mentor and raise the bar</strong> for engineers across the team on AI and ML best practices, prompt engineering, and production readiness.</p> </li> <li> <p><strong>Partner cross-functionally</strong> with Product, Engineering, Data, Ops, and CX to identify high-leverage AI opportunities and ship them.</p> </li> </ul> </div><p><br></p><b>Where You'll Have Impact</b><div> <h3 style="margin-top: 0pt; margin-bottom: 6pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; font-weight: 400;">A non-exhaustive list of areas we are actively building in or want to:</span></h3> <ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <h3 role="presentation" style="margin-top: 12pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-weight: 400;">Conversational AI for customer support, dispute resolution, and seller assistance</span></h3> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <h3 role="presentation" style="margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-weight: 400;">Automated order handling, escalation routing, and workflow orchestration</span></h3> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <h3 role="presentation" style="margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-weight: 400;">Personalized discovery, recommendations, and search relevance</span></h3> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <h3 role="presentation" style="margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-weight: 400;">Listing quality, including auto-generated titles, descriptions, categorization, and image understanding</span></h3> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <h3 role="presentation" style="margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-weight: 400;">Trust and safety, including fraud signals, anomaly detection, and content moderation</span></h3> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <h3 role="presentation" style="margin-top: 0pt; margin-bottom: 4pt;"><span style="font-size: 11pt; font-weight: 400;">Internal agent tooling for ops and CX teams</span></h3> </li> </ul> </div><p><br></p><b>Qualifications</b><div><span style="text-decoration: underline;"><strong><span style="font-size: 13pt; font-family: Arial, sans-serif;">Required</span></strong></span> <ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">5+ years building production software</span></strong><span style="font-size: 11pt;">, with at least 2 years shipping LLM and ML-powered features at scale.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Strong Python</span></strong><span style="font-size: 11pt;"> for backend services, scripting, data pipelines, and ML tooling.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Working ability in TypeScript and React</span></strong><span style="font-size: 11pt;"> for integrating AI features directly into product surfaces.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Production experience with major LLM providers</span></strong><span style="font-size: 11pt;"> (Gemini, Claude, GPT) covering tool and function calling, structured outputs, streaming, prompt caching, and cost control.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Deep understanding of Retrieval Augmented Generation (RAG)</span></strong><span style="font-size: 11pt;">: document ingestion, chunking, embedding generation, vector databases (pgvector, Pinecone, Weaviate, or similar), hybrid retrieval, and reranking.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Solid grounding in embeddings and vector search</span></strong><span style="font-size: 11pt;">: dense vs. sparse representations, similarity metrics, indexing strategies (HNSW, IVF), and dimensionality tradeoffs.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Strong ML and NLP fundamentals</span></strong><span style="font-size: 11pt;">: transformer architectures, tokenization, fine-tuning vs. prompting tradeoffs, classification, ranking, and evaluation methodology.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Experience with scripting and automation</span></strong><span style="font-size: 11pt;"> for data preparation, model evaluation harnesses, and offline analysis.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Comfortable with relational databases</span></strong><span style="font-size: 11pt;"> (PostgreSQL), caching layers (Redis), REST, SSE, WebSockets, and event-driven architectures.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><strong><span style="font-size: 11pt;">Production experience</span></strong><span style="font-size: 11pt;"> with observability, A/B testing, and rolling out model changes safely.</span></li> </ul> <span style="text-decoration: underline;"><strong><span style="font-size: 13pt; font-family: Arial, sans-serif;">Nice to Have</span></strong></span> <ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Experience with recommendation systems, learning to rank, or search relevance at scale.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Marketplace or C2C background covering buyer and seller dynamics, disputes, fraud, and payouts.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Multimodal model experience, including vision and image understanding for listings.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Arabic NLP or bilingual product experience.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Experience with agent frameworks (LangGraph, custom orchestrators) and the judgment to know when to use them.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Fine-tuning, LoRA, distillation, or hosting open weight models in production.</span></li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"><span style="font-size: 11pt;">Open source contributions to LLM tooling, eval frameworks, or retrieval libraries.</span></li> </ul> </div><p><br></p><b>What We Care About</b><div> <ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <p style="margin-top: 12pt; margin-bottom: 0pt;"><strong><span style="font-size: 11pt;">Ship over the architect.</span></strong><span style="font-size: 11pt;"> Lean code, no premature abstractions, no half-finished frameworks.</span></p> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <p style="margin-top: 0pt; margin-bottom: 0pt;"><strong><span style="font-size: 11pt;">Measurement-driven development.</span></strong><span style="font-size: 11pt;"> Features ship with evals and metrics, not vibes.</span></p> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <p style="margin-top: 0pt; margin-bottom: 0pt;"><strong><span style="font-size: 11pt;">Ownership.</span></strong><span style="font-size: 11pt;"> From idea to deployment to monitoring the first real users.</span></p> </li> <li style="font-size: 11pt; font-family: Arial, sans-serif;"> <p style="margin-top: 0pt; margin-bottom: 4pt;"><strong><span style="font-size: 11pt;">Curiosity and range.</span></strong><span style="font-size: 11pt;"> This role spans many problem domains, and we want someone energized by that.</span></p> </li> </ul> </div><p><br></p><p></p>

Back to blog

Common Interview Questions And Answers

1. HOW DO YOU PLAN YOUR DAY?

This is what this question poses: When do you focus and start working seriously? What are the hours you work optimally? Are you a night owl? A morning bird? Remote teams can be made up of people working on different shifts and around the world, so you won't necessarily be stuck in the 9-5 schedule if it's not for you...

2. HOW DO YOU USE THE DIFFERENT COMMUNICATION TOOLS IN DIFFERENT SITUATIONS?

When you're working on a remote team, there's no way to chat in the hallway between meetings or catch up on the latest project during an office carpool. Therefore, virtual communication will be absolutely essential to get your work done...

3. WHAT IS "WORKING REMOTE" REALLY FOR YOU?

Many people want to work remotely because of the flexibility it allows. You can work anywhere and at any time of the day...

4. WHAT DO YOU NEED IN YOUR PHYSICAL WORKSPACE TO SUCCEED IN YOUR WORK?

With this question, companies are looking to see what equipment they may need to provide you with and to verify how aware you are of what remote working could mean for you physically and logistically...

5. HOW DO YOU PROCESS INFORMATION?

Several years ago, I was working in a team to plan a big event. My supervisor made us all work as a team before the big day. One of our activities has been to find out how each of us processes information...

6. HOW DO YOU MANAGE THE CALENDAR AND THE PROGRAM? WHICH APPLICATIONS / SYSTEM DO YOU USE?

Or you may receive even more specific questions, such as: What's on your calendar? Do you plan blocks of time to do certain types of work? Do you have an open calendar that everyone can see?...

7. HOW DO YOU ORGANIZE FILES, LINKS, AND TABS ON YOUR COMPUTER?

Just like your schedule, how you track files and other information is very important. After all, everything is digital!...

8. HOW TO PRIORITIZE WORK?

The day I watched Marie Forleo's film separating the important from the urgent, my life changed. Not all remote jobs start fast, but most of them are...

9. HOW DO YOU PREPARE FOR A MEETING AND PREPARE A MEETING? WHAT DO YOU SEE HAPPENING DURING THE MEETING?

Just as communication is essential when working remotely, so is organization. Because you won't have those opportunities in the elevator or a casual conversation in the lunchroom, you should take advantage of the little time you have in a video or phone conference...

10. HOW DO YOU USE TECHNOLOGY ON A DAILY BASIS, IN YOUR WORK AND FOR YOUR PLEASURE?

This is a great question because it shows your comfort level with technology, which is very important for a remote worker because you will be working with technology over time...