• Build, train, and refine machine learning and deep learning models using time-series, sensor, and behavioral data. • Integrate data from wearables, fitness tracking platforms, and device APIs to create a clear story from movement, patterns, and activity signals. • Develop and maintain data pipelines that support both batch and real-time analytics. • Own model deployment in production environments — your models won’t live in notebooks; they’ll live in the world. • Work closely with engineering teams to integrate ML models into mobile and web apps. • Support logic for fraud, spoofing, and anomaly detection, ensuring data reflects real human activity. • Make complex outputs easy to understand — not just for engineers, but for product and business users too.

Role Description We are seeking a Staff Applied Backend / ML Engineer to lead the design and implementation of production-grade, AI-driven systems that power intelligent products at scale. This is a deeply hands-on senior technical role responsible for: - Architecting distributed backend systems - Designing and deploying machine learning pipelines - Translating ambiguous business problems into robust, measurable solutions - Shipping hardened production systems — not just prototypes You will design high-performance APIs and data workflows, productionize ML models (training, evaluation, inference, monitoring), and ensure reliability, security, and scalability across cloud environments. This role is ideal for an engineer who thrives at the intersection of systems architecture, applied ML, and product impact, and can move from whiteboard design to production deployment without handoffs. What You Will Do - Backend & Distributed Systems - Architect and implement scalable backend services (REST / gRPC, async systems, event-driven pipelines) - Design data-intensive workflows and ETL / ELT systems - Build high-throughput, low-latency APIs - Own service reliability, observability, and performance tuning - Define API contracts and integration patterns across services - Applied Machine Learning - Design ML pipelines end-to-end (data ingestion → feature engineering → training → evaluation → deployment) - Productionize models (batch and real-time inference) - Build embedding pipelines, ranking systems, and classification / extraction models - Implement experimentation frameworks and offline/online evaluation loops - Establish model monitoring (drift detection, performance tracking, alerts) - Cloud & Infrastructure - Deploy services across cloud environments (GCP, Azure, AWS) - Design CI/CD pipelines for ML and backend systems - Implement infrastructure-as-code practices - Ensure system security, compliance, and scalability - Technical Leadership - Set engineering standards and architectural direction - Mentor engineers across backend and ML domains - Collaborate with product, data, and leadership teams - Break down ambiguous problems into measurable execution plans - Drive long-term AI and platform strategy Qualifications - 6+ years of backend engineering experience - 2+ years of applied ML in production environments - Strong Python or Java expertise - Experience designing distributed systems at scale - Hands-on experience deploying ML models in production - Experience with SQL + NoSQL databases - Familiarity with event-driven architectures (Kafka, Pub/Sub, streaming systems) Requirements - Feature engineering and data preprocessing - Embeddings, ranking, or similarity systems - Model evaluation frameworks - Model serving (batch and real-time) - Experimentation / A/B testing systems - Production monitoring and observability - Cloud-native architecture (GCP / Azure / AWS) - Containerization (Docker) and orchestration (Kubernetes) - CI/CD pipelines - API performance optimization - Security best practices for distributed systems Nice to Have - Experience with large language models (LLMs) in production - Experience building data platforms or workflow orchestration systems - Experience with vector databases - Experience in B2B, industrial, or commerce platforms - Familiarity with infrastructure-as-code (Terraform, Helm) What Success Looks Like Within 6 months, you will have: - Designed and shipped a production ML-backed service - Established reliability and observability standards - Improved performance and cost-efficiency of core systems - Mentored engineers and elevated technical quality across the team

• Researching the applicability of cutting-edge AI technology in our features • You will work across multiple technologies around a core including: Python, AWS (EKS, S3, RDS, Terraform, etc.), AI/ML/Data Science libraries (Google ADK, pandas, faiss, etc.) • Developing reusable AI evaluation frameworks • Designing agentic AI systems • Delivering AI powered features • Creating performance- and cost-optimised services • Helping to build AWS platform infrastructure with Terraform, such as RDS instances or EKS clusters • Mentoring less senior developers on coding best practices (TDD with pytest, Pythonic code, etc.) • Writing and reviewing portions of detailed specifications for the development of moderately complex system components • Participating in development processes, and code reviews • Operating in a Scrum based development environment while collaborating with stakeholders • All other duties as assigned

• Define and drive the long term technical vision for Shopping ML across search, discovery, recommendations, and personalization. • Lead development of AI systems that fundamentally improve how customers discover products and shop on Instacart. • Architect large scale ML systems combining LLM reasoning, retrieval, ranking, recommendation models, and personalization. • Build and operate production ML systems powering real time shopping experiences across millions of users and products. • Identify foundational ML capabilities that unlock new customer experiences and accelerate experimentation across the organization. • Partner with senior leaders across product, engineering, and data science to shape technical strategy and roadmap. • Influence company wide ML architecture and contribute to major technical initiatives across Instacart. • Mentor senior/staff engineers through design reviews, architecture guidance, and hands-on collaboration.