Senior AI/ML Engineer - Production LLMs & Edge Deployment

Quantiphi; Atlanta (GA); Vor Ort; USD 140.000 - 210.000; Vollzeit

Zusammenfassung

Quantiphi is seeking a highly skilled Machine Learning Engineer to join our AI/ML team. You will own the path from experiment to production, fine-tuning models, evaluating performance, and optimizing inference for edge environments.

You will build data pipelines, design ML architectures, and curate instruction-tuning data while collaborating with cross-functional teams to deliver production-grade AI solutions for Fortune 1000 clients.

Qualifikationen

• Hands-on experience with fine-tuning LLMs and production deployment.
• Proficiency with Python, PyTorch, and Hugging Face ecosystem.
• Experience with vLLM, TensorRT-LLM, and quantization techniques.
• Knowledge of data pipelines, evaluation benchmarks, and ML deployment.

Aufgaben

• Model fine-tuning and evaluation.
• Data transformation and ML modeling.
• GPU and inference optimization, edge deployment.
• Build data pipelines for training and testing datasets.
• Collaborate with hardware and platform teams for integration.

Kenntnisse

LLM fine-tuning

LoRA/QLoRA

DPO

Python

PyTorch

Hugging Face

vLLM

TensorRT-LLM

CUDA profiling

Benchmarking

Data pipelines

Docker

Kubernetes

Linux

NVIDIA GPUs

Tools

Docker

Kubernetes

Linux

TensorRT

NvInfer

Jobbeschreibung

Quantiphi is seeking a highly skilled Machine Learning Engineer to join our AI/ML team. You will own the path from experiment to production, fine-tuning models, evaluating performance, and optimizing inference for edge environments.

You will build data pipelines, design ML architectures, and curate instruction-tuning data while collaborating with cross-functional teams to deliver production-grade AI solutions for Fortune 1000 clients.