Key Responsibilities

Generative AI Engineering & Architecture

- Lead the architecture, development, and production deployment of enterprise-grade Generative AI systems with a focus on scalability, reliability, and performance.
- Design and implement agentic workflows using LLMs, tools, and orchestration frameworks to enable intelligent autonomous behaviors.
- Build and integrate end-to-end GenAI pipelines, including model inference, RAG (Retrieval-Augmented Generation), embeddings, and application consumption via APIs.
- Collaborate with data and platform engineering teams to implement vector search, semantic retrieval, and contextual grounding for AI driven responses.
- Apply strong full stack engineering skills to build user-facing GenAI applications and robust backend systems.
- Develop scalable microservices and secure RESTful APIs to expose AI and ML capabilities across enterprise applications.
- Integrate GenAI functions with front-end interfaces built using contemporary web technologies.

Deployment, Operations, & Quality

- Lead model deployment, packaging, performance optimization, and lifecycle management in production environments.
- Ensure reliability and quality through test driven development (TDD), reusable component design, and modern architectural principles.
- Drive CI/CD based releases, containerized deployments, and DevOps practices for AI-driven applications.
- Provide technical mentorship to intermediate engineers and contribute to architectural design reviews.
- Champion engineering best practices, coding standards, and continuous improvement within Agile delivery teams.

Required Skills & Technical Expertise

Programming & Full Stack Development





- Proficiency in Python, Java, R, and SQL.
- Frontend and full stack development experience with ReactJS, HTML, CSS, and Node.js.

AI / ML & Generative AI

- Hands-on experience with TensorFlow, Keras, and PyTorch.
- Strong foundations in Generative AI, NLP, and NLU.
- Expertise working with Large Language Models (LLMs) and prompt engineering.

Agentic & GenAI Frameworks

- Experience with LangChain and familiarity with LangGraph and Ollama.
- Understanding of agentic system design, tool use, and workflow orchestration patterns.

Retrieval & Knowledge Foundations

- Strong knowledge of vector databases, RAG pipelines, semantic search, and embedding techniques.
- Demonstrated experience in microservices architecture, service-oriented design, and building scalable REST APIs.
- Expertise in API-driven development and integration patterns.
- Experience with model packaging, containerization, deployment pipelines, and operational monitoring.
- Hands-on experience with GitHub, GitHub Actions, and CI/CD automation.
- Familiarity with both SQL and NoSQL databases.

Preferred Qualifications

- Experience with cloud-based GenAI platforms (Azure OpenAI, AWS Bedrock, Google Vertex AI).
- Knowledge of distributed systems, high-availability architectures, and performance tuning.
- Prior experience leading technical initiatives or architectural decision-making.

Soft Skills

- Strong leadership, communication, and mentoring capabilities.
- Ability to work across cross-functional teams in fast-paced Agile environments.
- Strategic thinking with the ability to translate business needs into scalable AI solutions.

#J-18808-Ljbffr

📌 Sr. AI Engineer/Gen AI (Toronto)
🏢 Zodiac Solutions
📍 Toronto