• Developing MCP-like tools that expose network device APIs and CLI commands with clear descriptions, structured inputs/outputs, validation logic, and error handling • Managing tool metadata and supporting semantic search over available tools using a vector database • Creating golden user queries, expected answers, and query variations for specific tools, intents, and network-operation scenarios • Building automated tests to verify correct tool selection, tool parameterization, output structure, and end-to-end agent responses • Designing evaluation workflows combining deterministic checks, human review, and LLM-as-a-judge techniques • Refining prompts, tool descriptions, schemas, and agent workflows while monitoring regressions when new tools or changes are introduced • Developing production-quality Python code and tests

• Design and build cutting-edge AI applications – from MCP servers and voice-to-voice real-time apps to RAG bots and multi-agent systems. • Advise clients on AI strategy – join workshops, contribute to proposals, and help clients understand what's possible and what's right for them. • Build demos and PoCs – fast, purposeful, and client-ready without over-engineering. • Mentor junior engineers – share knowledge, review code thoughtfully, and help grow the team around you. • Shape our AI practice – contribute to shared tools, frameworks, and ways of working.

Role Description - Design, develop, and optimize solutions leveraging LLMs for NLP, conversational AI, and automated decision-making. - Integrate LLM capabilities across multiple platforms within the organization. - Research and experiment with emerging AI technologies, tools, and architectures to drive innovation. - Develop high-quality, scalable, and reliable Python code for AI applications. - Build and maintain APIs and services supporting AI and LLM deployment. - Deploy and manage AI solutions using cloud platforms, particularly Azure. - Analyze system performance, conduct error analysis, and continuously improve AI models. - Implement best practices for model training, data curation, and deployment. - Collaborate with cross-functional product and engineering teams to align solutions with business needs. - Contribute to a safe, inclusive, and accessible work environment where all Flighties feel welcomed, respected, and supported to thrive. - Other duties and tasks as assigned. Qualifications - Strong proficiency in Python with experience building production-level AI applications. - Proven experience in machine learning, especially NLP and AI-driven automation. - Experience deploying AI solutions in cloud environments, particularly Azure. - Solid understanding and hands-on experience with LLMs (e.g., OpenAI, Hugging Face). - Familiarity with tools like LangChain for prompt engineering (preferred). - Experience fine-tuning and deploying LLMs in production. - Knowledge of DevOps practices, including CI/CD, Docker/Kubernetes, and monitoring tools (e.g., Datadog). - Experience in the travel industry (preferred). - Reliable, high-speed internet connectivity required to support core job responsibilities, including but not limited to video conferencing, access to company systems, and secure handling of company data. - Bilingual French/English required, due to the nature of the role of dealing with both English and French team members. Benefits - Generous paid time off policy. - Travel perks/discounts. - Health & Wellness Programs and Employee Financial Wellness Services. - National/International Award Nights and Conferences. - Group benefits including extended health care, dental and vision, gender affirming care, fertility care. - Insurance including life, AD&D, critical illness, long term disability. - Employee Assistance Program. - RRSP/RPP with matching. - Tuition Reimbursement Program. - Employee Share Plan – Ability to purchase company stock on Australian Stock Exchange with partial company match, subject to terms and conditions. - Global career opportunities in a network of brands and businesses.

• Desarrollar plataformas internas, frameworks y aceleradores para soluciones de inteligencia artificial • Crear bibliotecas reutilizables, templates y toolkits para IA generativa y modelos de lenguaje • Diseñar pipelines de build, despliegue, evaluación y monitoreo de aplicaciones de IA • Integrar soluciones de IA con APIs, microservicios y plataformas corporativas • Impulsar la adopción de IA dentro del ciclo de desarrollo de software (SDLC) • Apoyar a equipos globales de producto, ingeniería y professional services en la implementación de soluciones • Presentar soluciones y nuevas funcionalidades a stakeholders, clientes y liderazgo ejecutivo • Traducir necesidades de negocio en soluciones técnicas escalables, seguras y viables