Software Engineer, Lamini AI

• Education: Bachelor’s degree in Computer Science or comparable fields
• Communication: Excellent written and verbal communication. Effective information sharing to audiences with vastly different backgrounds
• Experience: 4+ years of professional software engineering experience. Built and shipped software in production environments. Demonstrated experience in building complex systems using open-source tools & systems on the Kubernetes platform and evolving these systems to accommodate fast changes in customer requirements
• Languages: Proficient in Python, or other comparable languages. Familiarity with multiple languages
• Maintain good engineering quality: Clear and readable coding style in Python or comparable programming languages, ensure thorough and effective testing, comprehensive and straightforward documentation, holistic thinking of the long-term impact of the system
• LLM: Understand key concepts in LLMs. Can follow what’s going on in the market. Understanding of how LLM training and inference works. Understand distributed training and inference. Understand RAG, Agents, and other LLM application paradigms
• Team spirit: A collaborative mindset and desire to achieve top-tier results. To an inclusive team environment. Be serious, sharp focus, and be a solid team player
• Broad understanding of the Kubernetes ecosystem. ML systems, data pipeline, workload management, CI/CD, observability

Desirable

• Design and implement LLMs platform on Kubernetes: Design, build, and maintain an LLM platform on Kubernetes to support large language model tuning and inference, and other emerging LLM technologies
• Debug complex distributed system problems: Dive deep into complex distributed system problems on Kubernetes outside your direct access, for example, debugging on a customer’s own Kubernetes cluster without kubectl
• Solve customer problems: Fast response to customer requests and empathy to customers. Write comprehensive documentation to help customers better use the product
• Maintaining internal GPU fleet: Kubernetes-based cluster management system for managing GPU server clusters in our private data center
• Collaborate with ML & app engineers and product managers on platform features: Work closely with machine learning engineers, application engineers, and product managers to understand requirements and implement solutions