Description
As an AI Developer on our Optimization team, you will play a key role in advancing our core optimization capabilities by infusing them with cutting-edge artificial intelligence.
Our team is on a mission to significantly enhance our existing, high-performance optimization engine. You'll tackle a diverse range of complex problems - including optimization of vehicle routing and scheduling - for our customers at a massive scale.
You will join our team at a pivotal moment and be an integral part of building our next-generation AI/ML capabilities from the ground up. As a key contributor, your responsibilities will span the entire model lifecycle, from augmenting our current optimization models with advanced AI to implementing the infrastructure for their deployment and monitoring.
You will apply state-of-the-art techniques such as Deep Reinforcement Learning (DRL), predictive analytics, and Graph Neural Networks (GNNs), all while working with rich datasets including Geographic Information System (GIS) data.
Another core part of your role will be implementing best practices for safe AI/ML rollouts. You will help build and maintain robust A/B testing frameworks and canary deployment strategies, ensuring our innovations reach production safely and effectively.
In this highly collaborative position, you will work closely with other engineers and scientists, as well as cross-functional product teams in the US, to bring these intelligent services to life.
Responsibilities:
Develop, implement, and deploy state-of-the-art optimization models and machine learning algorithms to solve complex business problems like vehicle routing and resource scheduling.
Design and build robust, end-to-end MLOps pipelines—from data ingestion and feature engineering to model training, validation, and serving in a production environment.
Translate complex scientific concepts and research papers into production-quality code, primarily using Python and leveraging frameworks like PyTorch and optimization libraries.
Conduct rigorous offline and online experiments to validate model performance, ensuring that solutions are statistically sound, reliable, and deliver measurable business impact.
Required Qualifications:
4+ years of professional software development experience, with proficiency in languages such as Python/C#/Java.
Experience in the end-to-end ML lifecycle, including model training, deployment, inferencing, and addressing the challenges of scaling AI products.
Proficiency in safe AI/ML rollout methodologies, including canarying and A/B testing.
Proven ability to design and architect complex, high-performance systems that support AI workloads.
Demonstrated experience with cloud services (e.g., AWS, GCP, Azure).
Hands-on experience with common ML frameworks like PyTorch or TensorFlow, as well as libraries like scikit-learn and time-series models (e.g., Prophet, ARIMA, LSTM).
Strong problem-solving skills and the ability to write and optimize high-performance code.
Degree or equivalent relevant experience required. Experience will be evaluated based on the core competencies for the role (e.g. extracurricular leadership roles, military experience, volunteer roles, work experience, etc.).
Preferred Requirements:
Master's degree in Computer Science or a related field.
Strong technical expertise in Generative AI, particularly with RAG systems and Agentic workflows utilizing large language models.
Knowledge of Geographic Information Systems (GIS), including open-source routing engines and OpenStreetMap data.
Experience with distributed systems and microservices architecture.
Familiarity with build tools such as Bazel, CMake, or similar.
Knowledge and proven experience in C++.
Previous experience working in cross-functional and geographically distributed teams.
