Software Engineer (AI)

TL;DR

Software Engineer (AI): Develop and optimize ML model inference infrastructure focusing on large language models and performance enhancements. With an accent on quantization, speculative decoding, and GPU architecture, focus on debugging and scaling cutting-edge ML optimization techniques.

Location: San Francisco, New York, United States

Salary: $150000–$250000

Company

hirify.global powers inference for leading AI companies by combining applied AI research, flexible infrastructure, and developer tooling to bring cutting-edge models into production.

What you will do

• Implement and productionize advanced ML inference techniques such as quantization, speculative decoding, and LoRA.
• Debug and optimize ML performance using frameworks like TensorRT, PyTorch, and CUDA.
• Scale optimization techniques across various ML models, especially large language models.
• Collaborate with a diverse team to design innovative solutions.
• Own projects from conception to production deployment.

Requirements

• Location: Based in or able to work from San Francisco or New York, United States.
• Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or related field.
• Experience with Python or C++ and ML libraries like PyTorch and TensorRT.
• Familiarity with LLM optimization techniques and deep understanding of GPU architecture.
• Strong interest and experience in large language models.

Nice to have

• Experience with CUDA or similar technologies.
• Knowledge of Docker and Kubernetes.
• Proven track record in developing and deploying AI/ML inference solutions.

Culture & Benefits

• Competitive compensation with meaningful equity.
• Full medical, dental, and vision insurance coverage for employees and dependents.
• Generous PTO including company-wide Winter Break.
• Paid parental leave and company-facilitated 401(k).
• Exposure to a variety of ML startups for learning and networking.