Senior Full Stack Developer

Description:

We are seeking a Senior Full Stack Developer to own the architecture, development, and delivery of our AI-based SaaS products; from conversational and voice agents through to RAG pipelines, workflow automation, in-house language models, and production at scale. The role leads a full-stack engineering team and reports directly to the Project Lead.

Key Responsibilities

• Own the technical architecture, roadmap, and platform decisions for multi-tenant, AI-based SaaS products
• Lead and manage a full-stack engineering team, including sprint planning, code reviews, capacity planning, and performance management
• Design and deliver agentic AI systems: tool calling, multi-step workflows, memory, orchestration, and human hand-over
• Architect RAG pipelines end-to-end, from data ingestion and embeddings to vector search, re-ranking, and evaluation
• Evaluate and select LLMs, balancing accuracy, latency, cost, and hosting (API vs self-hosted)
• As our proprietary data grows, lead the development of in-house SLMs: dataset strategy, data preparation, fine-tuning, distillation, evaluation, and deployment
• Build real-time voice capabilities with STT and TTS, including streaming and latency optimisation
• Drive integrations with WhatsApp Business API, telephony (SIP/WebRTC), CRMs, ERPs, and third-party APIs
• Own production reliability, security, observability, and DevOps practices
• Translate business requirements into technical specifications, estimates, backlogs, and timelines, with weekly progress and risk reporting to the Project Lead

Leadership and Ownership

• Take full ownership of delivery; accountable for outcomes, not just assigning tasks
• Step in personally when a team member is blocked or falling behind, and get the work done
• Commit to deadlines and meet them; raise risks early, not at the last minute
• Stay calm and make sound decisions under pressure
• Hold the team to a high standard of quality, discipline, and accountability
• Lead by example: hands-on, reliable, and close to the work

Requirements

• 6–8+ years in software engineering, including 2+ years leading engineering teams and AI Bots.
• Full-stack developer with strong hands-on experience across front end, back end, databases, and APIs
• High level of knowledge in AI and machine learning, with a solid grasp of how modern AI systems are built, trained, evaluated, and deployed
• Proven track record of delivering projects on tight deadlines and taking ownership end-to-end
• Proven experience building and scaling a SaaS product in production
• Strong hands-on Python (FastAPI/Django) and full-stack capability (React/Next.js, PostgreSQL, Redis)
• Production experience with agentic AI and conversational AI agents
• Deep knowledge of RAG systems, vector databases (pgvector, Pinecone, Qdrant), and frameworks such as LangChain, LangGraph, or LlamaIndex
• Strong understanding of LLMs, both commercial (OpenAI, Anthropic, Gemini) and open-source (Llama, Qwen, Mistral), including prompt engineering, guardrails, and evaluation
• Practical experience building SLMs from proprietary datasets: data curation and labelling, fine-tuning (LoRA/QLoRA), distillation, quantisation, benchmarking, and serving (PyTorch, Hugging Face, vLLM, or similar)
• Hands-on experience with STT and TTS technologies (Whisper, Deepgram, ElevenLabs, Azure Speech, or similar)
• Experience with workflow automation (n8n, Make, or custom orchestration) and cloud/DevOps (AWS/GCP, Docker, CI/CD, GPU workloads)
• Hands-on enough to write production code, review pull requests, challenge design decisions, and unblock engineers
• Excellent English communication; Arabic is a strong plus
• Bachelor's or Master's degree in Computer Science, Software Engineering, AI, or equivalent