Backend Engineer, Inference Services for Real-Time Voice AI

Deepgram; United States; Remote; USD 120,000 - 160,000; Full time

Job summary

Deepgram is seeking a Backend Software Engineer to design and implement secure, scalable services for real-time speech processing. You will optimize inference, networking, and scheduling while delivering robust backend systems that power large-scale voice AI applications.

You will collaborate with Product and Engineering to shape new features, drive performance improvements, and build reusable, high-impact components for our Engine team. A strong command of Rust or C/C++ and Python is essential.

Qualifications

• Proficiency in Rust or C/C++ and Python for backend systems.
• Strong familiarity with UNIX-like environments and version control.

Responsibilities

• Improve core inference services for networking, speech processing, and latency optimization.
• Develop processes to measure and optimize service performance.
• Debug complex system issues across networking, scheduling, and high-performance computing.
• Rapidly customize backend services to support customer needs.
• Collaborate with Product to design and implement new services end-to-end.

Skills

Rust

C

C++

Python

UNIX

Git

Communication

Job description

Deepgram is seeking a Backend Software Engineer to design and implement secure, scalable services for real-time speech processing. You will optimize inference, networking, and scheduling while delivering robust backend systems that power large-scale voice AI applications.

You will collaborate with Product and Engineering to shape new features, drive performance improvements, and build reusable, high-impact components for our Engine team. A strong command of Rust or C/C++ and Python is essential.