Senior Machine Learning Engineer

<h2>Job Description</h2><p></p><p><b><span>Senior ML Engineer - AI Agents</span></b></p><h2></h2><p><span>Zendesk’s people have one goal in mind: to make Customer Experience better. Our products help more than 125,000 global brands (AirBnb, Uber, JetBrains, Slack, among others) make their billions of customers happy, every day.</span></p><p></p><p><span>Our team is dedicated to providing a state-of-the-art retrieval-augmented generation (RAG) platform across multiple channels; including customer service bots, email and search. In collaboration with ML scientists, we deliver high-quality AI products leveraging the latest tools and techniques, and serve them at a scale that most companies can only dream of. We’re passionate about empowering end-users to quickly find answers to their questions, and helping our customers make the most of their knowledge base.</span></p><p></p><p><b><span>We’re looking for a Senior ML engineer to join our team and play a key role in levelling up the RAG platform powering Zendesk!</span></b></p><h2></h2><h2><b><span>What you’ll be doing</span></b></h2><ul><li><p><span>Delivering AI-powered capabilities to our customers at Zendesk scale using the latest in LLM technology</span></p></li><li><p><span>Working closely with Product Management, ML Scientists and other ML Engineers to define feature scope and implementation strategies</span></p></li><li><p><span>Mentoring junior team members, as well as pairing with more experienced colleagues to foster mutual learning</span></p></li><li><p><span>Supporting our deployed services to ensure a high level of stability and reliability</span></p></li><li><p><span>Contributing to discussions regarding technical design and best practices</span></p></li><li><p><span>Writing clean and maintainable code to meet the team’s delivery commitments</span></p></li></ul><ul><li><p><span>Here some of the challenges you will be working on:</span></p><ul><li><p><span>How do we best expand our RAG platform to handle new use cases?</span></p></li><li><p><span>How do we optimize our system for both speed and cost-efficiency?</span></p></li><li><p><span>How do we incorporate multiple sources of context to improve the accuracy of our generated answers?</span></p></li><li><p><span>How do we make the best use of rapidly evolving LLM technologies?</span></p></li><li><p><span>And many more!</span></p></li></ul></li></ul><h2></h2><h2><b><span>What you bring to the role</span></b></h2><h3><b><span>Basic Qualifications</span></b></h3><ul><li><p><span>4+ years developing machine learning systems in Python</span></p></li><li><p><span>Solid understanding of architecture and software design patterns for server-side applications</span></p></li></ul><ul><li><p><span>Experience with managing and deploying cloud services with a cloud provider (AWS, GCP, Azure)</span></p></li></ul><ul><li><p><span>Experience building scalable and stable software applications</span></p></li><li><p><span>Collaborative and growth mindset, with a commitment to ongoing learning and development</span></p></li><li><p><span>Self-managed and agile, with the ability to problem-solve independently</span></p></li></ul><ul><li><p><span>Excellent communication skills, both written and verbal</span></p></li></ul><h3></h3><h3><b><span>Preferred Qualifications</span></b></h3><ul><li><p><span>Experience with using LLMs at scale</span></p></li><li><p><span>Experience in designing and implementing RAG systems</span></p></li><li><p><span>Experience with managing and deploying cloud services with AWS</span></p></li><li><p><span>Proven experience making data-driven engineering decisions; formulating hypotheses, conducting experiments, and analyzing results.</span></p></li></ul><h2></h2><h2><b><span>What our tech stack looks like</span></b></h2><ul><li><p><span>Our code is largely written in Python, with some parts in Ruby</span></p></li><li><p><span>Our platform is built on AWS</span></p></li><li><p><span>Data is stored in RDS MySQL, Redis, S3, ElasticSearch, Kafka, and Athena</span></p></li><li><p><span>Services are deployed to Kubernetes using Docker, with Kafka for stream processing</span></p></li><li><p><span>Infrastructure health is monitored using Datadog and Sentry</span></p></li></ul><h2></h2><h2><b><span>What we offer</span></b></h2><ul><li><p><span>Team of passionate people who love what they do!</span></p></li><li><p><span>Exciting opportunity to work with LLMs and RAG (retrieval augmented generation), rapidly evolving fields in AI</span></p></li><li><p><span>Ownership of the product features at scale, making a significant impact for millions of customers</span></p></li><li><p><span>Opportunity to learn and grow!</span></p></li><li><p><span>Possibility to specialise in areas such as security, performance, and reliability</span></p></li></ul><p></p><p><b><b>...and everything you need to be effective and maintain work-life balance</b></b></p><p></p><ul><li><p><span>Flexible working hours</span></p></li><li><p>