About this role
Aspire Software is looking for a Senior Software Developer to join our team in Lebanon.
Here is a little window into our company: Aspire Software operates and manages wholly owned software companies, providing mission-critical solutions across multiple verticals. By implementing industry best practices, Aspire delivers a time sensitive integration process, and the operation of a decentralized model has allowed it to become a hub for creating rapid growth by reinvesting in its portfolio.
About the Role : We’re hiring a Full-Stack AI Engineer who can own AI systems end-to-end, from application logic and backend services to AI integrations, prompt systems, and infrastructure. This role is focused on shipping production-grade AI, not experimentation or demos.
Key Responsibilities
Build and ship AI-powered features within existing SaaS productsDesign and develop new AI-native products (0→1) from concept to productionImplement backend services, APIs, and workflows supporting AI systemsBuild and maintain retrieval, embedding, and data pipelinesIntegrate LLMs, voice, and automation tools into production systemsDesign, version, and maintain prompt systems as part of the application layerDefine, implement, and iterate on AI evaluations to measure quality and reliabilityOwn deployment, monitoring, and iteration of AI features in productionCollaborate closely with product, design, and domain teams across the portfolioRequirements
Strong experience as a full-stack or backend engineerProven track record shipping AI-powered features to productionHands-on experience with RAG systems, embeddings, and vector databasesStrong understanding of backend architecture, APIs, and data modelsExperience integrating third-party APIs and servicesComfortable owning features end-to-end with minimal oversightAble to operate effectively in ambiguous, early-stage problem spacesSenior-level engineering judgment around reliability, performance, and tradeoffsLeverage AI coding IDE and agents such as Cursor and ClaudeLanguages: TypeScript and/or JavaScript, Python, or similarBackend: Node.js-based services, REST, GraphQL and event-driven APIsFrontend / App layer: React, Next.js, or similar frameworksDatabases: PostgreSQL (including pgvector), familiarity with structured/unstructured dataCloud & services: Experience building on modern cloud platforms and managed servicesSystem design: Services that scale across multiple tenants, products, and workloadsStrong competency in prompt engineering, including: Designing prompts for consistency, robustness, and scale Treating prompts as first-class engineering artifacts Iterating based on real-world usage and failure modesExperience designing and running AI evaluations, including: Defining success criteria for AI outputs Qualitative and quantitative evaluation approaches Using eval results to improve prompts, pipelines, and UXPractical understanding of LLM behavior, limitations, and cost tradeoffs
Preferred Skills and Qualifications:
LLM providers: OpenAI, Anthropic, GoogleVector databases: Pinecone, Weaviate, Qdrant, pgvectorAI frameworks: LangChain, LlamaIndex, or custom pipelinesVoice and speech: Whisper, ElevenLabs, VapiAutomation: n8n, Temporal, event-driven workflowsCloud and infra: Supabase, AWS, GCP, Vercel