This role focuses on configuring and supporting packaged or SaaS applications to meet evolving business demands. Key responsibilities include adapting features, managing releases, and ensuring robust system stability. Solutions are developed using standard tools, APIs, and low-code platforms, prioritizing alignment with business objectives and maintaining high compatibility and performance standards.

As an Inference Engineer, you will be instrumental in deploying and optimizing Large Language Models (LLMs).

Key duties involve hands-on work with serving stacks like vLLM, SGLang, or TensorRT-LLM. You will need a strong grasp of KV cache, batching, quantization, speculative decoding, and GPU optimization techniques. The role also requires benchmarking and optimizing latency, throughput, and memory utilization for LLM workloads.

The ideal candidate will possess a minimum of 3 years of experience specifically with Large Language Models (LLMs). Essential technical skills include proficiency with LLMs, along with experience in application integration via APIs and low-code platforms.

Candidates should also demonstrate the ability to effectively manage software release cycles and deployment processes. Experience in troubleshooting and resolving application performance issues is crucial. Familiarity with cloud-based application environments and their operational aspects is highly desirable.