• Develop pipelines for post-training tasks such as fine-tuning, evaluation, and model compression. • Implement scalable systems for model deployment, monitoring, and optimization. • Collaborate with researchers to validate experimental results in production contexts. • Build tools to automate benchmarking and regression testing. • Identify opportunities to improve efficiency in resource utilization and inference speed.

• Design and implement solutions for internal and external customers that exploit traditional machine learning and novel deep learning for next-generation satellite imagery analytics. • Plan and conduct research projects related to computer vision, time series analysis, content curation, probabilistic modeling, machine learning, predictive analytics, and geometric modeling. • Develop algorithms, models, and analytical tools for solving domain specific business problems. • Implement production quality analytics and models into the SpectraAI codebase (Python). • Collaborate with management and technical team on product strategy. • Collaborate with infrastructure developers and machine learning quality engineers to build robust analytics for production use cases. • Independently design and conduct experiments, tests hypothesis, implement model and loss function code, train models, and interpret experiment results following a machine learning process based on high level project objectives. • Other job-related duties as assigned.

Role Description We are seeking a Machine Learning Engineer III to own the infrastructure and systems that bring our data science models to life at scale. As our Data Scientists and Data Engineers build the models that understand and predict fan behavior, you build the platforms that serve those models in production. - Own the end-to-end ML infrastructure for recommendation, personalization, and LTV scoring systems, from feature engineering through model deployment and monitoring. - Build and maintain real-time and batch feature pipelines that serve low-latency predictions across the FanApp recommendation experience and cross-vertical personalization use cases. - Develop and scale model serving infrastructure that supports high-throughput, high-availability prediction across Fanatics' multi-product ecosystem. - Partner directly with Data Scientists to productionize LTV, churn, propensity, and ranking models and bridge the gap between experimentation and reliable production systems. - Build and maintain embedding pipelines that generate and refresh user and item representations powering personalization and affinity modeling at scale. - Implement and maintain A/B testing and experimentation infrastructure that enables reliable measurement of model and feature impact in production. - Collaborate with Data Engineers, Analytics Engineers, and Product teams to identify data sources, enforce data quality standards, and ensure models are fed with accurate, timely signals. - Drive continuous improvement of model accuracy, latency, and throughput through iterative optimization and monitoring frameworks. Qualifications - 3–5+ years in a machine learning engineering or data engineering role, with a degree in a quantitative field (Computer Science, Mathematics, Statistics, Engineering, or equivalent). - Strong Python proficiency and deep familiarity with production ML workflows, including packaging, versioning, deployment, and monitoring. - Hands-on experience with end-to-end ML platforms such as Databricks, AWS SageMaker, or equivalent, including model registry and serving components. - Proven experience building real-time feature pipelines and model serving systems that operate at scale with strict latency and uptime requirements. - Experience building or scaling recommendation or ranking systems in production, including embedding pipelines and low-latency inference infrastructure. - Solid understanding of distributed systems and large-scale data processing (e.g. Spark, Kafka, or equivalent). - Strong SQL proficiency and experience working with relational and dimensional data models. - Practical understanding of the mathematics underlying modern ML (linear algebra, probability, optimization) sufficient to partner effectively with Data Scientists on model design and debugging. - Familiarity with experimentation infrastructure and A/B testing frameworks, including exposure bias handling and metric integrity in production environments. Preferred But Not Required - Experience with feature stores (e.g. Feast, Tecton) and their role in supporting both real-time and batch ML use cases. - Experience with ML observability tooling, including drift detection, prediction monitoring, feature freshness alerting. Salary Range $117,000 — $167,000 USD Ranges will change based on country and state of residence, which are reflected in Geographical Zones defined by Fanatics Betting and Gaming. The range incorporates all of our Geographical Compensation Zones and is subject to change as the Zone associated with the actual offer is confirmed. In addition to the base and bonus, full-time employment, and more. For information about our benefits, please visit https://benefitsatfanatics.com/ . By submitting your application, you agree to our terms of service and acknowledge you have read our Candidate Privacy Policy.

• Architect Agentic Workflows: Design and implement multi-agent systems and autonomous workflows using flow-based orchestration and chain-of-thought reasoning. • Database & Vector Management: Manage enterprise data and high-dimensional vector embeddings within PostgreSQL, ensuring efficient retrieval for RAG (Retrieval-Augmented Generation) pipelines. • LLM Integration & Optimization: Lead the integration of LLMs via Azure OpenAI, focusing on prompt engineering, model parameter tuning, and performance monitoring. • Fine-Tuning: Identify opportunities where fine-tuning specific models can improve domain-specific performance and lead the data preparation and execution process. • System Orchestration: Build and manage AI middleware that connects LLMs to PostgreSQL, enterprise data sources, and third-party APIs. • Technical Leadership: Create playbooks for AI development and mentor the team on LLM best practices, ensuring AI-generated outputs meet rigorous accuracy standards.