ML Engineer, Recommendations

Who we are

We make a web-based inventory and purchasing system used by independent restaurants, breweries and small food manufacturers. Founded in 2008, the business writes the billing, metering and customer portal software that small water and electric utilities run on. Founded in 2008, we now have 140 employees.

What this job is

Ironwoodland is hiring for the ML Engineer, Recommendations role to take models from notebook to production and keep them working once they're there. Remote within Canada. The team meets in Toronto once a quarter, travel covered. Most of our work is async, and meetings are kept short.

What you'll do

Handle on-call for the ML services the team owns. Track experiments, artifacts and versions in MLflow or Weights & Biases. Maintain feature pipelines and a feature store such as Feast or Tecton. Develop RAG pipelines with embeddings, vector stores (pgvector, Pinecone, Weaviate) and rerankers. Document model cards, data sources and known failure modes. Build training pipelines in PyTorch or TensorFlow and run them on GPUs in AWS, GCP or Azure.

What we're looking for

Knowledge of LLM APIs, prompt design and evaluation methods. Familiarity with Docker, Kubernetes and a cloud ML platform (SageMaker, Vertex AI, Azure ML). Understanding of core ML concepts: overfitting, evaluation metrics, bias in training data.

Bonus points

CUDA or Triton kernel experience.

What we offer

Extended health and dental benefits. RRSP matching. Paid vacation. Life insurance. Flexible hours. Employee and family assistance program. Three weeks paid vacation to start.

Start: Immediately.

Demo job created on 11jobs for testing and demonstrations. It is not an actual opening at Ironwoodland.