AI Engineer
BDO View all jobs
- Calgary, AB
- Permanent
- Full-time
- Design, build, and deploy robust, scalable, production‑grade AI applications using frameworks such as LangChain, LlamaIndex, AutoGPT, and related LLM orchestration tools.
- Develop, refine, and optimize complex prompt strategies; manage model context windows; and fine‑tune models where required to maximize performance, accuracy, and cost efficiency.
- Integrate AI capabilities into existing enterprise environments through RESTful APIs, microservices, and cloud‑native architectures.
- Build, maintain, and optimize vector databases (e.g., Pinecone, Milvus, Weaviate) and design efficient data ingestion and embedding pipelines to support retrieval‑augmented generation (RAG) solutions.
- Monitor AI systems in production and proactively address issues related to hallucinations, latency, reliability, scalability, and token‑cost optimization.
- Collaborate closely with AI Architects, AI Studio Leads, ML Engineers, Data Scientists, Full‑Stack Developers, Service Line Labs, and Citizen Developers on firm‑wide initiatives and internal platforms.
- Support AI system documentation, lifecycle management, and control processes in alignment with ISO/IEC 42001 enterprise governance requirements.
- Adhere to established AI risk management, data governance, and security policies, and assist with model inventories, traceability, and change‑management activities.
- Participate in model testing and validation activities in accordance with the NIST AI Risk Management Framework, including mapping and measuring model risks.
- Support the implementation of risk‑mitigation controls and ongoing monitoring, and follow governance processes that promote transparency, accountability, and responsible AI use.
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, with 3–5 years of professional experience in AI, machine learning, or applied software engineering.
- Expert‑level proficiency in Python, with working familiarity in Java and/or TypeScript for enterprise application development.
- Deep hands‑on experience with leading AI and LLM frameworks, including OpenAI APIs, Anthropic, Hugging Face, and LangGraph, along with a strong understanding of LLM‑based application design.
- Proven experience designing and implementing retrieval‑augmented generation (RAG) and agentic AI systems, supported by a solid grasp of scalable, production‑grade AI architectures.
- Experience working with vector databases as well as SQL and NoSQL data stores, and hands‑on exposure to cloud platforms such as Azure AI / AI Foundry, AWS Bedrock, or Google Cloud Platform (GCP).
- Practical experience with DevOps and MLOps practices, including Docker, Kubernetes, and CI/CD pipelines for machine learning workloads.
- Familiarity with machine learning lifecycle and experiment‑tracking tools such as MLflow or Weights & Biases.