Logo of Huzzle

Lead ML Engineer - Recommender Systems



27d ago

  • Job
    Mid, Senior & Expert Level
  • Data
    Software Engineering
  • Cincinnati, +1
  • Quick Apply

AI generated summary

  • You need 4+ years building deep learning models, 3+ years with frameworks like Tensorflow/Pytorch, 3+ years in NLP/ML libraries, cloud platforms, Python/Spark, and optimizing pipelines. Strong problem-solving skills, retail/e-commerce experience, and ability to teach and collaborate are imperative.
  • You will design ML system architecture, train and optimize pipelines, deploy models, and lead tech initiatives for recommender systems. Collaborate cross-functionally and mentor junior data scientists for success in high-performing team.


  • Bachelor’s/Master’s degree or equivalent in computer science, data science, statistics, mathematics, analytics, or related discipline.
  • 4+ years of proven experience building deep learning models for large-scale recommender systems.
  • 3+ years of experience using Deep Learning frameworks such as Tensorflow, Pytorch, Fast.ai, Mxnet or HuggingFace.
  • 3+ years working with NLP/ML libraries (spacy, scikit-learn, SparkNLP).
  • 3+ years of experience working with cloud platforms like Azure or GCP.
  • 3+ years pf experience working with Python and Spark with track record of optimizing pipelines for efficiency and scalability to handle increasing data volumes. Experience working with Databricks is a plus.
  • Strong understanding of the internal workings of different ML frameworks, and practical experience in customizing architectures and loss function for specific use cases.
  • Hands-on experience developing software tools that scale (i.e. Python packages) and using end-to-end tooling to develop, test, and deploy these tools (i.e. CI/CD)
  • Other data science-adjacent technology experience would be beneficial but is not required, including Docker, Rest APIs, Fast API, Linux, and basic shell scripting.
  • High level of independence, able to make time-sensitive decisions rapidly and solve urgent problems without escalation.
  • Natural curiosity, welcomes and embraces change.
  • Excellent problem-solving skills and a proactive approach to addressing challenges.
  • Prior experience in the retail or e-commerce industry is a plus.
  • Must be able to learn from others and teach others and work collaboratively as part of a highly interdependent team.
  • Ability to communicate complex ideas effectively to both technical and non-technical stakeholders.
  • Experience with training, developing, recruiting, coaching, and/or inspiring highly technical associates.


  • ML System Architecture. Design the architecture of a ML system, including all parts of the ML life cycle, model serving infrastructure and integration with other software components. Use advanced knowledge of different model architectures to implement ML algorithms and ensure scalability. Strong skills to choose appropriate data representation methods, utilizing tools and tech to integrate sciences into ML pipelines.
  • Training and Inference pipelines. Implement efficient ML training pipeline to automate the process of loading data, preprocessing, training models and saving model artifacts. Design the inference pipeline to handle real-time or batch inference requests in production. Implement the inference pipeline to load the trained model artifacts, preprocess input data and generate predictions. Modularize the pipeline components to facilitate code reuse and maintainability.
  • Performance Optimization. Proactively work towards improving the performance of the ML models for speed, efficiency, and resource utilization. Research and implement different optimization techniques as needed for different recommender systems. Optimize inference pipeline for low-latency and high throughput performance.
  • API Development/Integration. Setting up APIs for model inference, monitoring model performance, and managing model versions. Develop, define, and integrate the different API endpoints that accepts user input and returns recommendations.
  • Model Deployment. Responsible for model deployment to cloud infrastructure like GCP, using containerization technologies like Docker and orchestration frameworks like Kubernetes in non-prod environments. Collaborate with other engineers to deploy ML models into production environments. Ensure model is load-tested to handle concurrent requests and that it performs well under different traffic conditions. Greater focus to ensure the ML systems are reliable, scalable, and efficient.
  • Monitoring and Logging. Responsible for setting up tools to track the model's performance, response times, and error rates. Configure logging to capture relevant information for debugging and auditing. Actively developing processes and standards for efficient model versioning, rollback processes, quality controls and health checks.
  • Tech leadership. Research state of the art machine learning algorithms, processes, patterns, and tooling to identify new opportunities for implementation across the enterprise. Proactively use their understanding of different algorithms and frameworks for ML and distributed systems and computing to build scalable and reliable ML systems.
  • Collaborate with cross-functional teams. Collaborate closely with other data scientists, data engineers, and full stack engineers to implement data science solutions. Actively work with platform engineers and full-stack software engineers in managing ML applications, recommending changes to writing infrastructure code and other IAC tools to setup a scalable infrastructure. Drive innovations in utilizing ML pipelines such as Vertex AI Pipelines for streamlined operations, metadata tracking, and continuous modeling experiences. Proactively work with data engineers to efficiently manage, share, and reuse machine learning features for both offline and online settings.
  • Mentoring. Provide guidance and mentorship to junior data scientists, especially on code and methodologies, and developing and sustaining technical pipelines for all parts of data science life cycle. Contribute to talent acquisition efforts, and work towards building a high-performing data science team


What is the main responsibility of the Lead ML Engineer in the Relevancy Team?

The main responsibility of the Lead ML Engineer in the Relevancy Team is to build relevant and personalized customer experiences for Kroger's E-commerce site through the development of search and recommender systems.

A retail data science, insights and media company creating more personalized and valuable experiences for shoppers.

Founded Year

Mission & Purpose

84.51° is a retail data science, insights and media company. We help the Kroger company, consumer packaged goods companies, agencies, publishers and affiliated partners create more personalized and valuable experiences for shoppers across the path to purchase. Powered by cutting edge science, we leverage 1st party retail data from nearly 1 of 2 US households and 2BN+ transactions to fuel a more customer-centric journey utilizing 84.51° Insights, 84.51° Loyalty Marketing and our retail advertising solution, Kroger Precision Marketing.