AI Platform Engineer

Role Overview

Maintain GPU training & inference clusters, build internal model API services, connect AI reasoning systems with front-end investment research workflows.

Key Responsibilities

• Manage, scale, and monitor internal GPU compute infrastructure for model training and inference.
• Optimize model inference latency and throughput using tools like TensorRT, vLLM, and ONNX.
• Develop robust, high-performance REST/gRPC APIs for AI model consumption by internal teams.
• Bridge the gap between backend AI reasoning systems and front-end investment research tools.
• Implement MLOps best practices, including CI/CD for machine learning pipelines.

Required Qualifications

• 3+ years of experience in MLOps, DevOps, or backend software engineering.
• Strong proficiency in Docker, Kubernetes, and cloud compute infrastructure.
• Experience deploying, monitoring, and scaling machine learning models in production environments.
• Solid programming skills in Python and systems languages like Go or C++.

Preferred Qualifications & Skills

• Experience serving massive-scale language models (LLMs) in production.
• Familiarity with hardware-level GPU optimization and CUDA profiling.