AI Developer - InQ

Aspire Software is looking for a AI 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 Job

Design, build, and ship full stack applications (modern front-end frameworks like React, plus API and service layers) where AI capabilities are core to the product, not bolted on Build LLM-powered features end-to-end: prompt and context engineering, RAG pipelines, structured outputs, and agent workflows integrated with product data and APIs Use AI-assisted development tools (Claude Code, Copilot, Cursor) as a force multiplier owning architecture and code quality while delegating implementation speed to AI Design and maintain evaluation frameworks for AI features: golden datasets, automated evals, regression testing on prompt/model changes, and production monitoring for drift and quality Own features from ambiguous requirements through production deployment including CI/CD, observability, and post-launch iteration AI Product Development Hands-on experience integrating LLM APIs (OpenAI, Anthropic, or similar) into production applications used by real customers. Prompt engineering fluency: system prompts, few-shot examples, structured outputs, tool/function calling, chain-of-thought patterns. Understanding of token economics: cost per call, context management, model selection tradeoffs across feature types. Experience building quality evaluation and output validation frameworks around AI features. Awareness of AI-specific risks: hallucination, prompt injection, data leakage, output inconsistency.

Desired Candidate Profile

Hands-on experience integrating LLM APIs (OpenAI, Anthropic, or similar) into production applications used by real customers. Prompt engineering fluency: system prompts, few-shot examples, structured outputs, tool/function calling, chain-of-thought patterns. Understanding of token economics: cost per call, context management, model selection tradeoffs across feature types. Experience building quality evaluation and output validation frameworks around AI features. Awareness of AI-specific risks: hallucination, prompt injection, data leakage, output inconsistency.