Instacart
Senior Machine Learning Engineer II, Fulfillment, Matching and Positioning
Vaga remota de Machine Learning com fit claro de localização do candidato.
PublicadaAdicionada recentemente
Países elegíveis1 país aceito
Sinal de senioridadeSenior
Modelo de trabalhoRemoto
Locais aceitos para candidatos
Estados Unidos
Resumo da vaga
Senior Machine Learning Engineer II, Fulfillment, Matching and Positioning
Requisitos e responsabilidades
Conteúdo da vaga extraído em seções para revisão mais rápida.
About the Job
- Design, implement, and deploy algorithms for order batching, real-time shopper assignment, routing, and marketplace positioning using techniques such as MIP/CP-SAT, heuristics/metaheuristics, and learning-to-rank.
- Own the full model lifecycle: problem formulation, data pipelines and features, offline evaluation and simulation, A/B testing, staged rollouts, and ongoing monitoring/observability.
- Build reliable, low-latency services in Python (and, where performance dictates, C++ or Go) that integrate with solvers (e.g., OR-Tools, Gurobi, CPLEX) and run on cloud infrastructure with Docker/Kubernetes.
- Partner with product, operations, and data science to define roadmaps and success metrics; deliver measurable impact to on-time rates, shopper utilization, cost per order, and customer experience.
- Leverage experimentation and causal methods along with offline counterfactual replay/simulation to validate changes and de-risk launches.
- Contribute to engineering excellence through code reviews, design docs, robust testing, and participation in an on-call rotation for mission-critical fulfillment services; mentor peers and raise the technical bar.
Minimum Qualifications
- Bachelor’s degree in Computer Science, Operations Research, Electrical Engineering, Applied Mathematics, or a related field (or equivalent practical experience).
- 5+ years of professional experience building and shipping ML and/or optimization systems to production.
- 3+ years formulating and solving large-scale combinatorial optimization problems (e.g., VRP, matching, scheduling) using solvers such as OR-Tools, Gurobi, or CPLEX (MIP/CP-SAT) and heuristic methods.
- Proficiency in Python and SQL, including writing production-quality code with testing, profiling, and code review practices.
- Hands-on experience deploying algorithms/models as microservices with Docker and Kubernetes on a major cloud provider (GCP or AWS), including monitoring, alerting, and dashboards.
- Experience designing and operating low-latency decision services in high-throughput environments (targeting sub-second P95 response times).
- Practical experience with A/B testing or online experimentation platforms, from hypothesis through analysis and rollout decisions.
- Strong collaboration and communication skills with engineering, product, and data science stakeholders.
Preferred Qualifications
- Master’s or PhD in Operations Research, Computer Science, Electrical Engineering, Applied Mathematics, or a related quantitative field.
- Domain experience in logistics, ride-hailing, delivery, or marketplace optimization at scale.
- Familiarity with reinforcement learning or contextual bandits for online decision-making and exploration/exploitation tradeoffs.
- Experience with geospatial data, routing APIs, and graph algorithms.
- Background in building simulation frameworks and counterfactual evaluation for decision systems.
- Experience with streaming data and real-time feature computation (e.g., Kafka, Flink) and feature stores.
- Proficiency in C++ or Go for performance-critical components.
- Track record of mentoring engineers and leading cross-functional projects to measurable outcomes.
- Experience participating in an on-call rotation for production ML/optimization services.
Vagas similares
Mantenha uma lista reserva.
Stack
Use estas tags para comparar vagas remotas similares.
Elegibilidade de localização
Candidatos devem aplicar apenas quando o país do perfil estiver listado aqui.
Seu perfilPaís não definidoEntre para comparar seu país com esta vaga.
Fluxo de contratação
O WithMira mostra a vaga e depois envia candidatos para a aplicação da empresa.
1Confira fit da vaga, stack e elegibilidade de localização no WithMira.
2Abra a página de aplicação da empresa pelo link rastreado.
3Salve a vaga ou assine oportunidades similares antes de sair.