Data Scientist

About Tripstack

Founded in Toronto, Canada in 2016, Tripstack has been part of Etraveli Group since 2019. It is a B2B Flights as a Service provider and a world leader in virtual interlining.

Operating from offices in Canada, India, and Poland, Tripstack is the gateway into Etraveli Group’s world leading tech platform - giving partners access to global flight content, virtual interlining, and a full suite of services including payments, fraud prevention, pricing, and customer support. As a world leader in virtual interlining technology, Tripstack connects non-partner, low-cost and full-service carriers, enabling the creation of unique and flexible itineraries through a simple, cost-effective API.

Its technology ingest over 30B price points and handles over 240 million searches daily.

Through partnerships with airlines, OTAs, and other distribution channels across the globe, Tripstack expands networks, drives new revenue streams, and offers more choice at competitive prices, all backed by robust technology and traveler protection.

 

For more information, visit:

The role

We're looking for a driven and entrepreneurial Data Scientist to join our Data team. You will own the full machine learning lifecycle — from conceptualizing solutions to deploying and monitoring production-grade models — across high-impact use cases including fare prediction, caching optimization, search ranking, and VI risk modeling. You will be a key member of a cross-functional Data team at Tripstack, working closely with Engineering, Product, and Commercial stakeholders to turn complex data into decisions that move the business forward.

Responsibilities

• Predictive Model Development: Design and build predictive ML models from the ground up — owning the process from problem framing and data exploration through to feature engineering, training, validation, and production deployment.

• MLOps Pipeline Development: Build, maintain, and improve scalable MLOps pipelines in Spark, ensuring models are reliable, reproducible, and operable at scale in production environments.

• Real-Time & Streaming ML: Develop and deploy models that operate on streaming data, leveraging our Redpanda-based infrastructure to support low-latency, real-time inference at scale .

• Search Ranking & Relevance: Apply ML techniques to itinerary ranking and search result optimization, improving the relevance and competitiveness of results surfaced to our partners and end users.

• Experimentation & A/B Testing: Design and own the statistical framework for experiments — defining hypotheses, selecting appropriate test designs, and interpreting results to drive confident, data-backed decisions.

• Model Lifecycle Management: Take full ownership of deployed models: monitoring performance, managing drift, triggering retraining cycles, and evolving models as business needs change.

• Cross-Functional Collaboration: Partner with Data Engineers, Analysts, and business stakeholders to integrate model outputs into products and analytics workflows, ensuring insights are actionable and well understood.

• Insight Communication: Translate complex model outputs and analytical findings into clear, compelling narratives for both technical and non-technical audiences — connecting the work to business outcomes.

• Opportunity Identification: Proactively identify new areas where machine learning can create business value, and champion those initiatives from concept to delivery with minimal direction.

Requirements

• 5+ years of hands-on experience in data science or machine learning roles.

• Bachelor's degree in Computer Science with a focus on Data Science and Machine Learning.

• Demonstrated experience taking predictive models from conceptualization through to production deployment at scale.

• Strong command of MLOps principles and tooling, with specific experience building pipelines in Apache Spark (PySpark) and working with streaming data platforms such as Apache Kafka or Redpanda.

• Solid grounding in statistics and probability — including hypothesis testing, regression analysis, Bayesian methods, and experimental design — applied to real-world ML problems.

• Proficiency in Python and the standard ML stack (scikit-learn, XGBoost, PyTorch/TensorFlow, or equivalent).

• Hands-on experience with MLflow for experiment tracking, model versioning, and model registry management.

• Familiarity with Delta Lake or equivalent for managing large-scale structured data with ACID guarantees in a lakehouse architecture, including an understanding of feature store concepts and training/serving data consistency.

• Familiarity with Airflow — a working understanding of DAGs, task dependencies, and pipeline orchestration concepts is expected, though hands-on DAG development is handled by the Data Engineering team.

• Comfort working in a private cloud environment — including deployments on bare metal servers, VMs, and Kubernetes.

• Proven ability to operate independently, manage competing priorities, and deliver in a fast-moving environment.

• Strong interpersonal and communication skills with a track record of influencing decisions through data.

Additional Experience That Would Be Considered An Asset

• Graduate degree (Master's or PhD) in Computer Science, Statistics, or a related discipline.

• Experience with risk modeling in a high-volume, price-sensitive marketplace such as online travel, e-commerce, or financial services.

• Background in online travel (airlines, OTAs, or metasearch).

Benefits

We offer an opportunity to work with a young, dynamic, and a growing team composed of high-caliber professionals. We value professionalism and promote a culture where individuals are encouraged to do more and be more. If you feel you share our passion for excellence, and growth, then look no further. We have an ambitious mission, and we need a world-class team to make it a reality. Upgrade to a First Class team!

At Tripstack, we proudly believe in embracing diversity. This is true for our team, clients, communities and stakeholders. We are an equal opportunity employer and committed to creating a safe, healthy and accessible environment. We encourage applications regardless of race, colour, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or any other grounds protected by law. Please let us know if you need any accommodations during any part of the recruitment process.

Tripstack thanks all applicants for their interest, however only those selected to continue in the process will be contacted.

The targeted pay range for this position in the following location is / locations are:

Canada - Toronto Office : 100, 000 - 140,000 CAD / Annual Our pay ranges reflect the minimum and maximum target for new hire pay for the full-time position determined by role, level, and location.The pay range shown is based on our compensation structure in place at the time of posting and may be updated periodically based on business needs. Individual pay is based on additional factors including job-related skills, experience, and relevant education and/or training.

The targeted pay range listed reflects the base pay only and does not include bonus, or other benefits.

We use AI in our hiring process.
Learn more about us at

#tripstack #LI-Hybrid #LI-CM1