About This Role
Developing advanced machine learning systems that address complex business challenges is at the core of this role. The Machine Learning Engineer will create and refine systems that power Kensho products, ensuring that AI agents effectively utilize trusted data sources.
Responsibilities
- Develop advanced ML systems that solve complex business problems and power Kensho products.
- Build retrieval-driven AI agents that fetch, validate, and structure data from SP datasets, ensuring answers produced by LLMs are grounded in SP's data universe.
- Evaluate LLM-based agents by identifying and resolving performance gaps in both online and offline settings, addressing issues such as performance, latency, memory usage, compute efficiency, and feature consistency.
- Work with domain-specific data by leveraging proprietary structured and unstructured datasets, deep diving to gain domain understanding, and collaborating with Subject Matter Experts (SMEs).
- Scale ML applications by optimizing and scaling ML systems to support high demand, efficient resource utilization, and reliable production behavior.
- Reduce technical debt by proactively identifying areas of the stack that can be improved and proposing solutions that strengthen reliability and maintainability.
- Take initiative by scoping, planning, and executing ML initiatives that develop core capabilities across Kensho products.
- Collaborate across teams with Data, Product, Design, and Engineering to ensure smooth operations and contribute to long-term product vision.
- Improve user experiences by partnering with Product and Design to develop ML-driven functionality that enhances user workflows and aligns with business needs.
- Drive the ML lifecycle by engaging in all phases, from problem framing and data exploration to model deployment and production monitoring, ensuring continuous improvement.
Requirements
- Bachelor's degree or higher in Computer Science, Engineering, or a related field.
- 3+ years of significant, hands-on industry experience with machine learning, natural language processing (NLP), and information retrieval systems, including designing, shipping, and maintaining production systems.
- Strong proficiency in Python.
- Experience reading and understanding SQL databases and writing queries for specific access patterns.
- Proven experience building ML pipelines for data processing, training, inference, maintenance, evaluation, versioning, and experimentation.
- Demonstrated effective coding, documentation, collaboration, and communication habits.
- Strong problem-solving skills and a proactive approach to addressing challenges.
- Ability to adapt to a fast-paced and dynamic work environment.
- Experience working with machine learning libraries/frameworks for Large Language Model (LLM) orchestration, such as LangChain.
