A Bit About Loop

Loop partners with enterprise clients across retail, quick-service restaurants, e-commerce fulfillment and third-party logistics to design and operate efficient, auditable delivery networks. Through advanced route and territory design, optimisation and tailored data services, we reduce costs, improve service reliability and provide clearer operational visibility to our clients.

We combine product engineering with deep operational expertise and hands-on consulting to turn data into actionable insights that drive efficiency and ROI for large, distributed operations. If you want to help define the future of delivery intelligence — building tools and services that enterprises rely on — Loop is where you want to be!

Data Science at Loop

We're expanding our data science capability to meet enterprise demand and lift delivery quality across our key client accounts. The team already includes in-house data scientists who've delivered real ROI for clients.

We're hiring a Data Scientist to design, build and productionise algorithms and models that operate

reliably at enterprise scale. A background in ML Engineering — across cloud platforms, deployment

tooling and MLOps practices — is a strong advantage and will allow you to hit the ground running across the full model lifecycle. Candidates who are stronger on the science than the engineering side are welcome to apply; structured upskilling in ML Engineering will be expected as part of the role.

Daily Roles and Responsibilities

• Own end-to-end ML / optimisation projects: scoping, prototyping, model development, validation

and monitoring.

• Contribute to and help scale our core service offerings — Territory Planning (data-driven geofence

and zone design), Route Planning (daily trip creation and resource allocation) and Route

Optimisation (real-time stop sequencing) — building and improving the underlying algorithms,

models and analytical frameworks that power these services.

• Translate client requirements into clear technical specs and implementation plans — remove

ambiguity before development begins.

• Design, build and maintain Looker Studio reports leveraging well-designed, cost-efficient scheduled queries in BigQuery.

• Support ad hoc strategic consulting engagements, such as optimal service location analysis,

working directly with enterprise clients to deliver data-driven recommendations.

• Collaborate with the engineering team on productionising models: data pipelines, model serving, CI/CD, monitoring and retraining.

• Ensure code quality: tests, documentation, reproducibility, maintainable and modularised code.

• Mentor and support other Data Team members and external contractors.

• Be client-facing when required: present outcomes, justify tradeoffs and surface operational risks.

• Define and lift data and model quality standards — act as a quality gate for enterprise deliverables.

Technical Skills and Qualifications

Core — Required

• Bachelor's degree in Data Science, Computer Science, Statistics, Mathematics or a related field.

• 5+ years of applied data science / ML experience in industry or research-to- production contexts.

• Strong Python skills and hands-on experience with ML libraries (scikit-learn, XGBoost, LightGBM,

TensorFlow, PyTorch or similar).

• Solid SQL expertise and experience with large analytical stores (BigQuery preferred).

• Experience building scalable algorithms and systems with modularised code and a clear understanding of trade-offs between accuracy, efficiency and cost.

• Good software engineering practices: version control (git), unit tests, code reviews, documentation.

• Familiarity with Operations Research (OR) techniques and optimisation frameworks (e.g. OR-Tools,

PuLP or similar).

• Geospatial data analysis experience. (highly advantageous)

ML Engineering — Advantageous

• Production ML experience: model deployment, pipeline orchestration, serving, monitoring and

retraining.

• Familiarity with MLOps tooling — e.g. MLflow, Vertex AI Pipelines, SageMaker Pipelines, Azure ML or Kubeflow.

• Containerisation and orchestration: Docker and Kubernetes.

• CI/CD practices adapted for ML workloads.

• Model serving: REST API endpoints for real-time or batch inference (e.g. FastAPI, Cloud Run,

SageMaker Endpoints, Azure ML Online Endpoints).

• Model monitoring: data drift, concept drift and performance degradation detection.

Cloud Platforms — Advantageous

• Hands-on experience with GCP, AWS or Azure for ML workloads. GCP is preferred as our data

infrastructure runs on GCP/BigQuery.

1. GCP: Vertex AI, BigQuery ML, Cloud Run, Cloud Storage, Dataflow.

1. AWS: SageMaker, S3, Lambda, Step Functions, Glue.

1. Azure: Azure Machine Learning, Azure Data Factory, Blob Storage, AKS.

• Cloud certifications — GCP Professional ML Engineer, AWS ML Specialty, Azure AI Engineer Associate or Azure Data Scientist Associate. (optional — advantageous)

Soft Skills

• Attention to detail and strong analytical and problem-solving skills.

• A partnership mindset — comfortable working alongside enterprise clients in a collaborative,

consultative way to co-develop data-driven solutions.

• Strong communication skills, including the ability to translate complex technical findings into clear,

actionable insights for non-technical stakeholders.

• Ability to work well both independently and within a team.

• Comfortable managing remote collaboration with internal and contracted team members.