Logo
VELVETECH LLC

MLops Engineer

VELVETECH LLC, Miami, Florida, us, 33222

Save Job

From IT consulting to building custom tech solutions and integrating enterprise systems — our services span a full range of software development to accelerate your project delivery. With high-level expertise in technologies, data, and processes, we ensure you get digital solutions that perfectly blend into your business environment to boost its efficiency. Position overview

We are seeking an experienced

MLOps Engineer

with deep expertise in

cloud services

such as

Azure ML

and

AWS SageMaker , providing end-to-end MLOps operations and services. The successful candidate will cover the entire

ML lifecycle , including

developing/writing pipelines

for model development,

preparing training data, training models, deploying models , and

monitoring and testing models

in production. Additionally, this role requires

LLMOps experience , particularly in deploying

open-source LLM models

such as

Llama, Mistral, R1 . This role will also involve experimenting with different ML/LLM models, calculating and monitoring evaluation metrics, and providing the best AI solutions for various marketplace-related tasks, such as product category classification, product data enrichment, dynamic price optimization, and price and demand forecasting. Technologies

MLOps and Cloud Services – Azure ML Studio, AWS SageMaker, MLflow, Databricks Containerization and Orchestration – Docker, Kubernetes Model Monitoring and Deployment – BentoML, Ollama, Hugging Face LLMOps Tools and Libraries – vLLM, LiteLLM, LangChain, Langfuse CI/CD and Workflow Automation – Gitlab, Azure DevOps Responsibilities

MLOps and ML Lifecycle Management:

Develop and optimize

MLOps pipelines

for scalable model development and deployment. Automate

model training, deployment, monitoring, and testing

workflows. Manage

data pipelines , ensuring efficient training data preparation. Implement

model performance tracking and versioning

using MLflow. LLMOps and Large-Scale AI Deployments:

Deploy and fine-tune

open-source LLM models

for various business use cases. Utilize

vLLM, LiteLLM, BentoML, Ollama

for optimized LLM inference and deployment. Monitor and evaluate

LLM performance

across different metrics including

latency, accuracy, and cost-effectiveness . AI Solutions for Marketplace Optimization:

Develop AI-based solutions for

product category classification

and

product data enrichment . Implement

dynamic price optimization models

and

forecast price and demand trends . Build AI systems to select optimal recommerce channels for selling products based on various business factors, including price seasonality and inventory costs. Requirements

Software engineering:

Python, ML frameworks (PyTorch, TensorFlow), microservices, data pipelines. Problem-solving:

Evaluating and fine-tuning ML/LLM models, tracking metrics, optimizing AI solutions. This position offers a unique opportunity to work at the

intersection of MLOps, LLMOps, and AI-driven business solutions . If you have the technical depth and passion for

building scalable, production-grade AI solutions , we encourage you to apply!

#J-18808-Ljbffr