AI Developer/Prompt Engineer architecting generative AI solutions for Levio, a digital transformation consultancy. Building cloud - native applications with AWS Bedrock, SageMaker, NLP, and LLM technologies.
About the role
- Senior Agentic AI Developer building reliable agentic AI systems for Osedea, a Montreal tech development firm. Designing production architectures, integrations, evaluations, and workflows for clients.
Responsibilities
- Design, develop, and deploy production-grade AI agents and agentic platforms and workflows for complex business challenges
- Architect systems combining agentic harnesses, LLMs, tool calling, external APIs, enterprise data, and existing software applications
- Build agent orchestration workflows including state management, context engineering, memory, and human-in-the-loop interactions
- Define and implement evaluation, testing, observability, and monitoring practices for agent reliability, performance, cost, and security
- Make architectural decisions balancing autonomy, predictability, scalability, cost, and maintainability
- Collaborate with clients and multidisciplinary teams to identify opportunities, assess technical feasibility, and translate business needs into practical AI solutions
- Own technical delivery from solution design and prototyping through deployment and continuous improvement
- Evaluate emerging models, frameworks, and development approaches
- Share knowledge, mentor colleagues, and contribute to Osedea's Agentic AI development practices
Requirements
- 5+ years of professional software architecture and development experience
- Hands-on experience building production-grade agentic systems
- Strong software development and architecture fundamentals, including system architecture, APIs, asynchronous processing, testing, and cloud deployment
- Capacity for end-to-end infrastructure design: storage, compute, identity & policy management
- Demonstrated experience designing and delivering AI-powered applications beyond the proof-of-concept stage
- Solid understanding of agentic architectures, including tool use, orchestration, context management, and retrieval-augmented generation (RAG)
- Experience integrating harnesses, agents or LLMs with external services, internal systems, and existing enterprise data and infrastructure
- Ability to evaluate AI system quality and reliability, troubleshoot complex behaviours, and make informed technical trade-offs
- Comfortable working with fast-evolving technologies, tools, standards and best practices
- Builder mindset with strong architectural credentials and proficiency with agentic engineering building blocks and how they fit together
- Strong collaboration and communication skills, including the ability to navigate ambiguity, explain technical decisions to clients and teammates, and take initiative
- Intermediate or conversational French (minimum)
- Proficiency in Python and modern backend development practices
- Proficiency with LLM APIs and SDKs such as OpenAI, Anthropic Claude, or Google Gemini
- Proficiency with agent orchestration frameworks such as Microsoft Agent Framework, LangGraph/LangChain, OpenAI Agents SDK, or equivalent
- Proficiency with harnesses and plugin design using platforms such as Codex, Claude Code, or Pi
- Knowledge of ACP, MCP, Skill standards and other agentic engineering best practices
- Context engineering methods, including cache hit optimization
- Retrieval methods: RAG, embeddings, vector search, graph search and lookup
- Tool integration: function calling, API integrations, and patterns for connecting agents to external tools
- Quality and reliability practices: automated testing, agent evaluations, tracing, observability, and error handling
- Infrastructure experience with AWS, Azure, or Google Cloud, CI/CD, and production deployment practices
- Academic background is not specifically required; proven technical skills, curiosity, and practical experience are valued over a specific academic background or fixed technology stack
Benefits
- Competitive Salary and contribution to your pension plan (RRSP)
- Flexible hours of work and choose how you work
- Work from anywhere up to 8 weeks
- Paid sabbatical
- Wellness and productivity spending account
- Parental program
- Activities
- Training
Job title
Job type
Experience level
Salary
Not specified
Degree requirement
No Education Requirement
Tech skills
Location requirements
Report this job
Found something wrong with the page? Please let us know by submitting a report below.
Forward Deployed AI Lead shaping Anthropic AI strategies and operating models for Caylent cloud - services clients. Directing FDE implementation, executive workshops, adoption roadmaps, and account expansion.
AI Engineer operating production AI agents and reliability tooling for an AI marketing platform serving dental practices. Debugging LLM failures, integrations, monitoring, and scheduling systems.
Développeur IA senior concevant des architectures backend et intégrant LLM, RAG et agents chez Mila. Livraison de plateformes GenAI fiables avec Python, FastAPI et systèmes distribués.
Customer Service Representative handling global customer inquiries across phone, email, and chat. Supporting WorkMatePro’s staffing clients with issue resolution, records, sales follow - up, and CRM updates.
Développeur senior en IA agentique chez Osedea, concevant des systèmes intelligents pour des clients. Architecture, déploiement et amélioration de solutions IA prêtes pour la production.
Senior AI/ML software engineer developing AI strategy and scalable machine - learning components. Building FHIR - based healthcare data solutions for global health stakeholders at Smile Digital Health.
Applied AI Engineer improving Velixo Intelligence, an Excel - native ERP reporting and automation platform. Building LLM evaluations, observability, and cost optimizations for governed financial - system actions.
CAD Engineer training and evaluating AI agents in real CAD environments. Designing engineering geometry and reference solutions for a global technology platform.
CFD Engineer training and evaluating AI agents on expert - level fluid simulations. Building verified solutions and Python checks for a global technology platform.