A leading search AI company is seeking a Senior MLOps Engineer who will work on improving machine learning model inference within search workflows. You will enhance the scalability and reliability of services, collaborate with various teams, and optimize solutions for efficiency. The ideal candidate should possess over 5 years of experience in MLOps, with a strong background in operating ML models at scale and tuning GPUs. This role offers competitive pay and flexible working options.
Qualifications
5+ years of experience in an MLOps or related ML Engineering role.
Experience self-hosting & operating models at scale using frameworks like Ray.
Experience with specialized hardware, especially GPUs.
Responsibilities
Evolve the inference service to host LLMs.
Enhance service scalability and reliability.
Improve platform efficiency utilizing available infrastructure.
Skills
MLOps
Machine Learning Engineering
Production experience with Ray
GPU tuning via CUDA
Effective communication skills
Tools
Ray
KServe
Job description
A leading search AI company is seeking a Senior MLOps Engineer who will work on improving machine learning model inference within search workflows. You will enhance the scalability and reliability of services, collaborate with various teams, and optimize solutions for efficiency. The ideal candidate should possess over 5 years of experience in MLOps, with a strong background in operating ML models at scale and tuning GPUs. This role offers competitive pay and flexible working options.