AI Engineer

Role We are seeking an AI Engineer – Full Stack (Agentic) to design, develop, and deploy AI‑powered applications with a focus on Large Language Models and agent‑based systems. The role blends full‑stack software engineering with applied AI, delivering intelligent features for client and internal products. Responsibilities Design, develop, and deploy AI‑powered features and applications across the full stack (frontend, backend, APIs).

Build and integrate LLM‑based solutions (OpenAI, Gemini, Anthropic) into real‑world use cases. Develop and maintain agentic systems, multi‑agent orchestration, task delegation, and autonomous workflows. Implement RAG pipelines, embeddings, and vector search to enhance AI system performance.

Collaborate with technical leads and stakeholders to translate business needs into scalable technical solutions. Contribute to architecture decisions related to AI integration and application design. Ensure code quality, scalability, and maintainability through best practices and code reviews.

Participate in deployment processes, CI/CD pipelines, and cloud‑based infrastructure. Optimize the performance of applications and AI models in production environments. Write clear technical documentation and share knowledge within the team.

Stay up to date with AI and LLM advancements and propose relevant improvements. Implement LLM‑based features using prompt engineering, embeddings, and fine‑tuning techniques. Design and orchestrate agent‑based systems for complex workflows.

Build and maintain RAG architectures using vector databases such as Pinecone and FAISS. Evaluate and improve AI outputs based on relevance, accuracy, and business impact. Contribute to reusable AI components, tools, and internal frameworks.

Ensure responsible AI usage, including data privacy, security, and ethical considerations. Participate in all phases of the software development lifecycle, from ideation to deployment. Anticipate risks and dependencies, proactively addressing potential challenges before they arise.

Qualifications Bachelor’s degree in Computer Science or related field. 4–5 years of software engineering experience, with strong exposure to AI and LLM technologies. Hands‑on experience with LLM platforms such as OpenAI, Gemini, Anthropic. Strong understanding of prompt engineering techniques (zero‑shot, few‑shot).

Experience with embeddings, semantic search, and RAG architectures. Experience with agentic frameworks and multi‑agent orchestration systems. Familiarity with AI frameworks and tools such as LangChain, LangGraph, MLflow.

Understanding of LLMOps concepts including evaluation, monitoring, and iteration. Experience designing scalable, maintainable software architectures. Experience with CI/CD pipelines and DevOps best practices.

Hands‑on experience with cloud platforms (AWS, Azure, Google Cloud). Strong knowledge of relational and NoSQL databases (PostgreSQL, MySQL, MongoDB). Experience with containerization and orchestration technologies (Docker, Kubernetes).

Strong understanding of data security, privacy, and responsible AI practices. Excellent problem‑solving and analytical skills. Strong communication and collaboration abilities.

Ability to work autonomously while aligning with team objectives. You are a good fit if You are a hands‑on engineer passionate about building AI‑powered applications and solving complex technical problems. You enjoy combining software engineering and applied AI to deliver scalable, innovative solutions.

You thrive in collaborative environments, stay curious about emerging AI technologies, and take ownership of high‑quality work. You are proactive, execution‑oriented, and comfortable across both backend and frontend systems while contributing to modern AI architectures and workflows. Internal Tools Slack Github Google Workspace The tech stack varies depending on the problem to solve, but overall we use Typescript / Node .NET React / Vue Terraform Microservices REST APIs GitHub Actions OpenAPI / Contract‑first API AI tools and frameworks: LangChain, LangGraph, vector databases (Pinecone, FAISS), OpenAI APIs, embeddings, RAG architectures Working at Chrono Innovation Flexible schedule with a hybrid work model.

Offices in Montreal’s vibrant neighborhood, with a bright, open‑space work environment. Personalized collective insurance coverage. 24/7 physical and psychological telemedicine for you and your family members. Access to the ChronoCare well‑being program.

Paid training and courses through the Chrono University program. Opportunities to develop new skill sets and grow your career. Registered Retirement Savings Plan (RRSP) and Registered Education Savings Plan (RESP) options. #J-18808-Ljbffr