Weedmaps is looking for a Machine Learning Engineer to build and deploy sophisticated AI and machine learning systems that power their marketplace and e-commerce platform, addressing challenges like product matching, personalized recommendations, and data-driven optimizations in a rapidly growing industry.
Requirements
- Strong programming skills in Python and experience with modern LLM endpoints
- Experience with MLOps practices for model monitoring, maintenance, and lifecycle management
- Demonstrated expertise in machine learning algorithms and frameworks (e.g. TensorFlow, PyTorch, or scikit-learn) as well as modern LLM systems (Anthropic, OpenAI) with a proven track record of deploying models to production
- Proficiency in software engineering best practices, including version control, code review, testing, and documentation
- Strong understanding of data engineering principles and experience with data preprocessing, feature engineering, and data quality assurance
- Experience with cloud computing platforms, preferably AWS (particularly SageMaker and Bedrock)
- Experience using AI endpoints such as Claude or ChatGPT for embeddings and more advanced AI pipeline use cases such as hybrid ranking systems leveraging RAG with AI-based re-rankers that optimize specific metrics (e.g. precision)
Responsibilities
- Develop production-ready Python-based ML models with a focus on advanced NLP, similarity metrics, and product matching and recommendations
- Create and refine machine learning pipelines that can handle the unique challenges of our product data, including inconsistent naming and categorization
- Develop comprehensive evaluation frameworks including evals and metrics to benchmark ML model performance in real-world scenarios
- Implement automated evaluation pipelines to continuously monitor model performance in production
- Build and maintain scalable ML infrastructure using a mix of managed services (eg AWS SageMaker) and custom services (such as function as a service apps on Kubernetes)
- Implement best practices for model serving, versioning, and monitoring in production environments
- Optimize model deployment pipelines for reliability, performance, and cost-efficiency
Other
- The ideal candidate is a hands-on ML practitioner with strong software engineering fundamentals who can build end-to-end systems that deliver measurable business impact.
- You will collaborate extensively with cross-functional teams, including Product to understand user needs and translate them into ML solutions; Engineering to integrate ML systems into our broader ecosystem; Data and Analytics to leverage insights and coordinate on data strategies; as well as stakeholders across the business to ensure ML initiatives are aligned with company objectives.
- History of effective collaboration with cross-functional teams to deliver ML solutions that drive measurable business results
- Experience communicating complex ML concepts to both technical and non-technical stakeholders
- Bachelor's degree in Computer Science, Data Science, or related quantitative field
