Remote Senior Software Engineer, AI Inference

Description:

• The Senior Software Engineer, AI Inference position at Deepgram involves implementing and optimizing inference code for speech AI models.
• Responsibilities include developing, testing, and deploying application code for massive-scale production services.
• The role requires debugging complex system issues related to networking, scheduling, and high-performance computing interactions.
• Building internal tooling for analysis and benchmarking to enhance efficiency improvements is a key aspect of the job.
• Experimenting with optimization techniques for machine learning workloads on NVIDIA GPUs and implementing successful strategies in production is essential.

Requirements:

• Ability to work collaboratively in a fast-paced environment and adapt to changing priorities.
• Proven industry experience in building and shipping production services.
• Strong proficiency in a lower-level language such as C, C++, or Rust.
• Experience in breaking down large projects into smaller experiments or incremental improvements.
• Expertise in a machine learning framework like Torch or Tensorflow.
• Familiarity with GPU programming using tools like CUDA or libraries such as cuDNN, cuBLAS, etc.

Benefits:

• Opportunity to work with a trailblazing research team on novel model architectures.
• Ownership of features from collaboration with researchers to testing in production.
• In-depth involvement with profilers, hardware architectures, and inference algorithms.
• Collaborative work environment within a humble team focused on mission-critical production services.
• Professional growth and impact in the AI industry with cutting-edge technology.