Backend Engineer- Inference Services
$150k - $220k • Remote • USA - Remote • FullTime
Posted 3mo ago
About the job
Deepgram is seeking a Backend Software Engineer to join the Engine team, focusing on the design and implementation of the company's speech processing products. This role involves building secure, robust, and scalable services for speech processing, efficient distributed compute orchestration, and optimized scheduling. The ideal candidate will possess strong skills in writing reusable code to overcome technical challenges and a good intuition for user experience. You will play a key role in the Product and Engineering teams, driving high-impact products from conception to completion. Deepgram operates with an AI-first mindset, expecting all team members to actively use and experiment with advanced AI tools, integrating them into their daily work and workflows to push technological boundaries.
Responsibilities
- Improve core inference services, including networking, speech processing, audio transcoding, and latency/memory optimization.
- Develop processes for measuring, building, and optimizing services for maximum system performance.
- Debug complex system issues involving networking, scheduling, and high-performance computing interactions.
- Rapidly customize backend services to meet customer needs.
- Partner with Product to design and implement new services, features, and products end-to-end.
Requirements
- 3+ years of industry experience.
- Programming experience in Rust (or C, C++), with competence in Python.
- Excellent written and verbal communication and organizational skills.
- High level of experience and understanding of version control, preferably Git.
- Comprehensive experience with UNIX-style systems.