Shape and enhance packaged or SaaS applications as a Packaged/SaaS Application Engineer. This role is pivotal in tailoring application features, managing release cycles, and ensuring robust system stability. You will leverage standard tools, APIs, and low-code platforms to deliver solutions that precisely meet business needs while maintaining optimal compatibility and performance.

This position offers an exciting opportunity to work with advanced technologies, including hands-on experience with serving stacks like vLLM, SGLang, or TensorRT-LLM. A deep understanding of KV cache, batching, quantization, speculative decoding, and GPU optimization is essential. You will also be involved in benchmarking and optimizing application performance metrics such as latency, throughput, and memory utilization.

- Drive independent work and develop into a subject matter expert within the team. - Actively participate and contribute valuable insights during team discussions. - Propose and implement effective solutions to address complex work-related challenges. - Collaborate closely with stakeholders to capture and translate their requirements into precise application configurations. - Proactively monitor application performance and swiftly troubleshoot issues to ensure uninterrupted system reliability. - Maintain comprehensive documentation of configuration changes and build knowledge bases to foster team learning and development.

- Minimum of 3 years of hands-on experience in Large Language Models (LLMs). - Proficiency with serving stacks such as vLLM, SGLang, or TensorRT-LLM is a must. - Solid grasp of KV cache, batching, quantization, speculative decoding, and GPU optimization techniques. - Experience in benchmarking and optimizing latency, throughput, and memory utilization. - Familiarity with agentic, tool-calling, and multi-user LLM workloads is beneficial. - Strong understanding of application integration using APIs and low-code platforms. - Proven ability to manage software release cycles and deployment processes effectively. - Experience in troubleshooting and resolving application performance issues. - Exposure to cloud-based application environments and their operational aspects.