Senior Machine Learning Engineer - Graph ML

We are looking for a Senior Machine Learning Engineer to join our Knowledge Enrichment team

at BenchSci.

You will help design and implement ML-based approaches to analyse, extract and generate

knowledge from complex biomedical data such as experimental protocols and from results from

several heterogeneous sources, including both publicly available data and proprietary internal

data, represented in unstructured text and knowledge graphs. You will work alongside some of

the brightest minds in tech, leveraging state of the art approaches to deliver on BenchSci’s

mission to expedite drug discovery. Knowledge Enrichment is at the core of this challenge as it

ensures we can reason over and gain insights from an extensive, accurate, and high quality

representation of biomedical data.

The data will be leveraged to enrich BenchSci’s knowledge graph through classification,

discovery of high value implicit relationships, predicting novel insights/hypotheses, and other ML

techniques. You will collaborate with your team members in applying state of the art ML and

graph ML/data science algorithms to this data.

You are comfortable working in a team that pushes the boundaries of what is possible with

cutting edge ML/AI, challenges the status quo, and is laser focused on value delivery in a

fail-fast environment.

Pay range: $160,000 - 200,000

We know compensation is an important part of choosing your next role. The range shown reflects our target hiring range, informed by market data, internal equity, and the role’s current scope. Often the mid-range is where we tend to fall, but individual offers may vary based on experience, skills, and the role scope.

You Will:

• * Analize and manipulate a large, highly connected biological knowledge graph constructed of data from multiple heterogeneous sources, to identify data enrichment opportunities and strategies.
• Work with data and knowledge engineering experts to design and develop knowledge enrichment approaches/strategies that can exploit data within our knowledge graph.
• Provide solutions related to classification, clustering, more-like-this-type querying, discovery of high value implicit relationships, and making inferences across the data that can reveal novel insights.
• Deliver robust, scalable and production-ready ML models, with a focus on optimizing performance and efficiency.
• Architect and design ML solutions, from data collection and preparation, model selection, training, fine-tuning and evaluation, to deployment and monitoring.
• Collaborate with your teammates from other functions such as product management, project management and science, and other engineering disciplines.
• Sometimes provide technical leadership on Knowledge Enrichment projects that seek to use ML to enrich the data in BenchSci’s Knowledge Graph.
• Work closely with other ML engineers to ensure alignment on technical solutioning and approaches.
• Liaise closely with stakeholders from other functions including product and science.
• Help ensure adoption of ML best practices and state of the art ML approaches within your team(s).
• Participate in various agile rituals and related practices.

You Have:

• * Minimum 3, ideally 5+ years of experience working as an ML engineer.
• Some experience providing technical leadership on complex projects.
• Degree, preferably PhD, in Software Engineering, Computer Science, or a similar area.
• A proven track record of delivering complex ML projects working alongside high performing ML, data and software engineers using agile software development.
• Demonstrable ML proficiency with a deep understanding of how to utilize state of the art NLP and ML techniques.
• Mastery of several ML frameworks and libraries, with the ability to architect complex ML systems from scratch. Extensive experience with Python and PyTorch.
• Track record of contributing to the successful delivery of robust, scalable and production-ready ML models, with a focus on optimizing performance and efficiency.
• Experience with the full ML development lifecycle from architecture and technical design, through data collection and preparation, model selection, training, fine-tuning and evaluation, to deployment and maintenance.
• Familiarity with implementing solutions leveraging Large Language Models, and a deep understanding of how to implement solutions using Retrieval Augmented Generation (RAG) architectures, including both Graph RAG and Vector RAG.
• Experience with graph machine learning (i.e. graph neural networks, graph data science) and practical applications thereof. Your experience working with Knowledge Graphs, ideally biological, and a familiarity with biological ontologies complement this.
• Experience with complex problem solving and an eye for details such as scalability and performance of a potential solution.
• Comprehensive knowledge of software engineering, programming fundamentals and industry experience using Python.
• Experience with data manipulation an