Software Architect

Summary

Join Encoura's Data Science Team as a mission-driven Software Architect, playing a foundational role in shaping the software architecture for predictive modeling, data enrichment, and analytics products. Lead development efforts for high-performing, scalable systems managing massive datasets and streamlining model scoring pipelines. Design robust cloud-native architectures, implement intelligent agentic systems, and build high-throughput pipelines for predictive model validation. Architect end-to-end ML pipelines within the Databricks ecosystem and leverage Delta Lake for reliable data storage. Design systems for model lifecycle management and collaborate with data scientists, product managers, and engineers. Develop GraphQL and REST APIs and leverage AWS, Docker, and Databricks to scale computational resources. Implement system observability practices to monitor predictive workflows. Within a year, serve as the go-to architect for Encoura’s next-gen data products.

Requirements

• Hands-on with Databricks, or equivalent Spark-based data processing environments
• Python (advanced) and associated libraries: Pandas, PySpark, Polars, NumPy
• Proven experience designing data pipelines and backend systems for ML/AI workflows
• Cloud platforms, especially AWS (S3, EC2, ElastiCache, Lambda, SageMaker, Glue, Athena, etc.) and Kubernetes
• Familiarity with Streamlit, GitHub workflows, and CI/CD best practices
• Expertise in development and exposing ML models with REST and/or GraphQL API

Responsibilities

• Architect Scalable Systems: Design robust cloud-native architectures to support the orchestration of predictive models, and real-time data workflows across a growing analytics product portfolio
• AI-Enabled Automation: Spearhead implementation of intelligent agentic systems to streamline and automate data ingestion, transformation, model scoring, and decision routing
• Data Science Integration: Build and maintain high-throughput pipelines for predictive model validation, automatic retraining, and model scoring. Optimize a PySpark-based ETL job and deploy your changes via CI/CD pipelines to a cloud environment
• Databricks Architecture & Optimization: Design and optimize Databricks workspaces, clusters, and workflows to support large-scale data processing, machine learning operations, and production model serving
• AI-Enabled Data Pipelines: Architect end-to-end ML pipelines within the Databricks ecosystem, from data ingestion to model deployment and monitoring
• Delta Lake Implementation: Leverage Delta Lake for reliable data storage, versioning, and ACID transactions that support our predictive models and data services
• MLflow Integration: Design systems for model lifecycle management, including experiment tracking, model registry management, and deployment workflows
• Cross-Functional Collaboration : Partner with data scientists, product managers, and engineers to deliver architecture that balances flexibility, performance, and innovation
• API & Platform Design: Develop GraphQL and REST APIs to expose data science services to internal platforms and client-facing dashboards
• Cloud & Container Expertise: Leverage AWS, Docker, and Databricks to scale computational resources, optimize model serving, and support high-volume data operations
• Observability & Optimization: Implement system observability practices to monitor the performance of predictive workflows in production

Preferred Qualifications

• Containerization with Docker; orchestration experience a plus (e.g. we standardize on Kubernetes)
• Experience in higher ed, enrollment tech, or education analytics is a plus but not required
• Knowledge of large-scale model management, ML ops, and distributed preferred computing
• Exposure to business intelligence, cost optimization strategies, or institutional research domains preferred

Benefits

• Comprehensive health and benefits package
• 401k company match that vests immediately upon participation
• Paid holidays and a generous PTO policy
• Paid parental leave