AI Software Engineer

About the role

Sana Commerce builds an ERP-integrated B2B commerce platform for manufacturers, distributors and wholesalers. It is looking for an AI Engineer in Alexandria to expand its product at speed, building features that help customers grow and contributing to a higher level of engineering excellence. The work involves designing and delivering AI-powered features such as agents that act on real commerce data (catalog, pricing, inventory, orders).

Key responsibilities

• Design, develop and deliver AI-powered features using modern LLM frameworks and toolchains (e.g. LangChain, AWS Bedrock, Microsoft Fabric, Cloudflare Agents)
• Build RAG systems, AI agents and dynamic workflows, understanding the underlying agentic loop
• Work in a cross-functional team (Engineering, Product, Design) to integrate AI into a distributed product
• Apply AI engineering principles end to end, from context and tool design through evaluation, deployment and continuous improvement
• Build eval and feedback loops that gate releases: curated datasets, metrics and thresholds that block regressions
• Design for failure by building the recovery path before the happy path
• Contribute to LLMOps and AI observability, improving reliability, evaluation and monitoring pipelines
• Stay up to date with emerging AI tools and help shape the product vision and roadmap

Required profile

• Proven commercial experience building and deploying production-grade AI applications
• 4+ years of web application engineering experience
• Strong software engineering (back-end, front-end nice to have) and SDLC fundamentals (design patterns, SOLID principles, complex MACH systems, CI/CD, testing)
• Practical knowledge of LLMs and their components (tokenization, attention, embeddings, vector search) and common limitations
• Hands-on experience with RAG pipelines, agents and Vector Stores, with judgement on when retrieval is the wrong tool
• Familiarity with LLMOps practices, monitoring, evaluation and feedback loops
• Has built real evals tied to business impact, including dataset, metrics, thresholds and the regression caught
• Cost and latency literacy, and strong working knowledge of cloud technologies