Back End Engineer, AI/ML

Role Description We are looking for a Software Engineer to join one of our engineering teams here in Sheffield. Working as part of the Pendo Listen engineering group you will build tools that help our customers transform product feedback into insights they can use to improve their own software experiences. You will focus on developing LLM-powered features and building backend systems that enable our platform to extract insights from qualitative customer data. Familiarity with machine learning techniques, particularly around large language models (LLMs), is essential for this role. As a back end engineer, you will join a collaborative team that values scalability, maintainability, and innovation, working alongside engineering, product, and design teams. Role Responsibilities Design, build, and maintain scalable backend services to support LLM-powered features. Collaborate with machine learning engineers and data scientists to integrate LLMs and other AI models into our platform. Write maintainable, high-quality code and documentation to ensure long-term sustainability. Gain a deep understanding of the backend technology stack (Go, GCP, APIs, databases) and related tools. Gain familiarity with backend technologies such as Python and NodeJS. Take ownership of tasks and projects, collaborating with team members to break down work into manageable components. Actively participate in agile ceremonies, refinement sessions, and other team activities. Communicate ideas, concerns, and potential solutions effectively with technical and non-technical stakeholders. Exhibit a growth mindset by demonstrating self-awareness and a commitment to continuous learning and improvement. Collaborate with product managers and designers to plan, design, and implement backend features that support new product capabilities. The role is hybrid remote/office based in our Sheffield office in Kelham Island. Working in the office 3 times a week. Minimum Qualifications 2+ years of experience building backend services for production applications. Experience working with large language models (LLMs) or similar machine learning technologies. General understanding of machine learning techniques, particularly around classification and topic extraction. Proficiency with a backend programming language (Go preferred, but not required; Python is a plus). Solid understanding of backend architecture, including APIs, databases, caching, and distributed systems. Strong foundation in software engineering principles, including data structures, algorithms, and software design. Preferred Qualifications Bachelor's or Master’s degree in Computer Science, Engineering, or a related technical field. Experience deploying and maintaining machine learning models in production. Familiarity with tools and frameworks for working with LLMs (e.g., OpenAI APIs, LangChain). Familiarity and experience with Search Databases (e.g., ElasticSearch) and semantic search. Knowledge of cloud platforms and CI/CD workflows. Experience writing and maintaining unit and integration tests for backend systems. Experience with scalable data processing frameworks or message queues. Interest in staying up-to-date with advancements in AI and machine learning. Experience with frontend technologies and frameworks (e.g. VueJS, Angular).

#J-18808-Ljbffr