Agero is looking to solve the problem of optimizing dispatch decisions to directly optimize cost efficiency and service levels through the development of a next-generation Dispatch Optimization platform.
Requirements
- Deep understanding of Data Science, ML techniques (e.g., XGBoost, PyTorch, Transformers), optimization methods (MIP/Linear/Stochastic), and architectural requirements for low-latency, real-time decision services
- Skilled in Python, SQL, and Cloud (AWS) MLOps and Data pipelines (Airflow, SageMaker, or equivalents)
- Experience with machine learning models and research paradigms (e.g., LLMs, Generative AI, Causal Inference, Foundation Models)
- Experience with cloud-native service development and deployment
- Experience with Agile/Scrum framework and project management tools
- Experience with data pipelines and data engineering
- Experience with security and regulatory compliance
Responsibilities
- Lead the process to define and select the optimal Data Science, Machine Learning, and Optimization strategy
- Guide the design and implementation of end-to-end cloud-native Python services (batch/streaming) that execute constrained optimization algorithms and deliver low-latency, real-time dispatch decisions
- Define and foster the MLOps strategy, ensuring the automation of model training, validation, A/B testing/rollout, and production monitoring using tools like SageMaker, Airflow, or similar industry platforms
- Actively manage technical debt and ensure the prompt resolution of critical production issues by maintaining robust monitoring, alerting, and logging systems
- Collaborate with Architecture to guide platform design and identify opportunities to integrate emerging technology trends
- Establish metrics for product performance (e.g., NPS / cost telemetry), monitor operational health, identify failure modes, and drive rapid iteration cycles based on empirical data
- Maintain rigorous operational standards, manage platform development and deployment costs, and ensure security and regulatory compliance activities, including external audits and system documentation
Other
- Bachelor's Degree (Master's preferred) in Computer Science, Computer Engineering, Data Science, Operations Research, or a closely related quantitative field
- 6+ years relevant experience in Data Science, ML Engineering, or Operations Research, with significant experience transitioning research models into production-grade, scalable systems
- 2+ years proven experience in engineering management or a similar technical leadership role, specifically managing Data Science or ML Engineering teams
- Willingness to travel is required, as you may need to attend on-site team meetings from time to time
- Flexibility to adapt to changing priorities and fast-paced environments
