Backend Engineer- Inference Services

📋 Description

• • Deepgram is at the forefront of the rapidly expanding Voice AI economy, a market projected to reach trillions of dollars. We provide best-in-class real-time APIs for speech-to-text (STT) and text-to-speech (TTS), enabling developers and organizations to build sophisticated, production-grade voice agents at scale. Our technology powers voice offerings for over 1,300 organizations and more than 200,000 developers worldwide, including industry leaders like Twilio, Cloudflare, Sierra, Decagon, Vapi, Daily, Cresta, Granola, and Jack in the Box. Deepgram's proprietary voice-native foundation models are accessible via cloud APIs, as well as self-hosted and on-premises software solutions, delivering unparalleled accuracy, minimal latency, and exceptional cost efficiency. With a recent Series C funding round led by top-tier global investors and strategic partners, Deepgram has processed an astounding 50,000+ years of audio and transcribed over 1 trillion words, solidifying our position as the undisputed global leader in voice technology understanding.
• • As a Backend Software Engineer on the Engine team, you will play a pivotal role in shaping and implementing Deepgram's core products. Your responsibilities will encompass the design and development of secure, highly robust, and scalable services essential for advanced speech processing. You will architect efficient, distributed compute orchestration systems, optimize scheduling algorithms, and contribute to numerous other critical backend functionalities. Your expertise in crafting highly reusable code, adept at navigating complex technical challenges, will be complemented by a keen intuition for creating delightful user experiences. You will be an integral and influential voice within Deepgram’s Product and Engineering departments, driving the lifecycle of high-impact products from initial concept through to successful launch and iteration.
• • Key responsibilities include enhancing Deepgram’s core inference services, focusing on critical areas such as networking protocols, sophisticated speech processing algorithms, efficient audio transcoding, and meticulous optimization of latency and memory utilization. You will be instrumental in developing and refining processes for measuring, building, and optimizing these services to achieve maximum system performance and reliability.
• • You will tackle and resolve complex system issues, which may involve intricate interactions between networking components, scheduling mechanisms, and high-performance computing environments. A significant part of your role will involve rapidly customizing backend services to precisely meet the evolving needs of our diverse customer base, ensuring our solutions remain agile and responsive.
• • Furthermore, you will collaborate closely with the Product team, contributing your technical expertise to the design and end-to-end implementation of new services, features, and potentially entirely new products. This collaborative approach ensures that our technical development is tightly aligned with market demands and customer value.
• • This role is ideal for individuals who thrive in a dynamic, fast-paced, and impact-driven environment where continuous learning and the rapid acquisition of new skills are not just encouraged but are a fundamental aspect of daily work. You will enjoy the challenge of balancing product and feature maturity decisions, discerning when to implement minimally invasive changes versus when to engage in more detailed, foundational design work.
• • You will be a key contributor to the evolution of our inference infrastructure, ensuring it remains scalable, performant, and reliable as Deepgram continues its rapid growth. Your work will directly impact the quality and speed of our speech AI services, which are used by millions of users globally.
• • We foster an AI-first culture, expecting all team members to actively use, experiment with, and integrate advanced AI tools into their workflows. Success in this role will be measured by your ability to leverage AI effectively to deliver exceptional results, continuously pushing the boundaries of what is possible with these technologies. You should be comfortable adopting new models and methodologies quickly, adapting to the rapid pace of AI innovation, and contributing to an environment of constant learning and experimentation.
• • This role offers a unique opportunity to work with cutting-edge AI technology, contribute to a product that is transforming an industry, and be part of a highly collaborative and innovative team. You will have the autonomy to make significant technical decisions and see the direct impact of your work on Deepgram's success and the broader Voice AI landscape.