AI Data Scientist

Firesafe AI; Edmonton; On-site; CAD 80,000 - 100,000; Full time

Job summary

A technology firm specializing in wildfire detection seeks an AI Data Researcher to lead efforts in designing deep learning models for wildfire prediction. You will work with environmental data, develop time-series models, and build a simulation-oriented ML pipeline. Ideal candidates have expertise in AWS, deep learning, and are comfortable in a fast-paced team environment. Send your resume and relevant project details to apply.

Qualifications

• Hands-on experience with deep learning frameworks for time-series data.
• Practical experience in AWS with machine learning deployments.
• Effective communication and ownership in prototypes to production.

Responsibilities

• Lead design, experimentation, and deployment of deep learning models.
• Develop time-series prediction models using environmental data.
• Build a simulation-oriented ML pipeline for wildfire behavior.

Skills

Deep learning for time-series or sequential data

Data wrangling and feature engineering

Collaboration in small teams

Education

Eligible to work in Canada

Tools

PyTorch

TensorFlow/Keras

AWS (S3, EC2, etc.)

Job description

About FireSafe AI:

FireSafe AI is a leading innovator in AI-powered wildfire detection and risk mitigation technologies. We help communities, governments, and businesses protect lives and assets by providing real-time wildfire analytics, early warning systems, and actionable insights through our advanced AI solutions.

Position Overview:

We’re working on an IRAP-funded R&D project focused on building deep neural networks (DNNs) for wildfire spread simulation on an web/cloud platform.

As an AI Data Researcher, you will lead the design, experimentation, and deployment of deep learning models for wildfire prediction.

You’ll work end-to-end: from data preparation and feature engineering, to model design and evaluation, to integration.

Key Responsibilities:

Develop and refine time-series prediction models (e.g. RNNs, LSTMs, Transformers) using:

• Historical and real-time environmental data (weather, vegetation/fuel, terrain, etc.)
• Records of past wildfire or related events

Own the data science workflow:

• Data collection, cleaning, and feature engineering for temporal and spatial datasets
• Designing experiments, running training jobs, and analyzing results

Help build a simulation-oriented ML pipeline that:

• Ingests environmental data
• Produces predictions or risk scores related to wildfire behaviour and spread
• Integrates with our existing web/cloud services

Collaborate with a small team of engineers and domain experts to:

• Translate real-world constraints (fire behaviour, operations, etc.) into model requirements
• Iterate quickly on ideas and make pragmatic choices to hit milestones by March 31

Qualifications:

Eligible to work in Canada on a T4 contract for the full project duration

Strong hands‑on experience with deep learning for time-series or sequential data, ideally in Python with PyTorch or TensorFlow/Keras

Solid skills in:

• Data wrangling and feature engineering (Pandas, NumPy, etc.)
• Training, validating, and comparing ML models on real, noisy data

Practical experience on AWS with at least some of:

• S3, EC2, ECS/EKS, Lambda, or similar compute / storage services
• Any ML deployment experience (SageMaker, custom Dockerized services, etc.)
• Comfortable working in a small, fast-moving team, communicating clearly, and taking ownership from prototype to production

Nice to Have

• Experience with environmental modeling, climate / weather data, remote sensing, or wildfire risk
• Familiarity with geospatial data and tools (e.g. raster/vector data, GDAL, GeoPandas)
• MLOps / experiment tracking tools (MLflow, Weights & Biases, SageMaker Experiments, etc.)
• Building APIs and services (REST, gRPC, or GraphQL)
• Previous work on research-style or government-funded projects is a plus (IRAP, NSERC, etc.)

How to Apply

Send us:

• Your CV or LinkedIn profile
• A short note on:
• Relevant time-series / deep learning projects
• Any environmental / geospatial / wildfire experience
• Your AWS experience in practice (what you used and for what)
• (Optional) Links to GitHub, publications, or portfolio

to: [e-mail]