C++ Developer (VLLM, SGlang, TensorRT)

Description

We are the speech synthesis team at GigaPlatform. We create and develop speech synthesis technologies. We solve the full cycle of synthesis tasks, including synthesis itself, including on LLMs, NLP tasks, and much more. Recently, we released a major update to our synthesis, which is head and shoulders above what existed before, especially in terms of naturalness and "human-likeness" (https://habr.com/ru/companies/sberbank/articles/966640/). We do not plan to stop at what has been achieved and are already preparing an even higher-quality synthesis model. Currently, we are expanding our production implementation department team.

We are looking for talented DL engineers who understand how models work at the level of mathematics and hardware.

Responsibilities

• low-level optimization and working with "hardware"
• maintaining infrastructure for interacting with LLMs
• deploying new architectures to production

Requirements

• experience in the field of deep learning, including with LLMs
• deep knowledge of CUDA and Python
• knowledge and experience with the TensorRT, vLLM, and SGlang frameworks
• experience with C++ is a plus

Conditions

• comfortable, modern office near Kutuzovskaya metro station
• opportunity to choose a convenient schedule – office/hybrid/remote (within Russia)
• annual bonus
• corporate gym and recreation areas
• more than 400 educational programs from SberUniversity for professional and career development
• extended VHI, preferential insurance for family, and corporate pension program
• employee mortgage under a discount program
• free SberPrime+ subscription, discounts on products from partner companies
• referral bonus for recommending friends to the Sber team.