Distributed ML Systems Engineer- Inference

This job was posted over 30 days ago, so it has most likely closed. See newer jobs like it.

Written by AI from the job title and company, not by Together AI, so some details may not match this job. The employer's own page has the real description.

Job Overview

As a Distributed ML Systems Engineer - Inference at Together AI, you will be tasked with the design, development, and enhancement of scalable machine learning inference systems that leverage distributed architectures. Your role is crucial in ensuring that our machine learning models can be deployed effectively across diverse environments. You will work closely with cross-functional teams to optimize the performance of our inference pipelines, ensuring they meet the highest standards of efficiency, reliability, and scalability.

Job Responsibilities

• Design and implement distributed machine learning inference frameworks tailored for scalability and performance.
• Collaborate with data scientists and software engineers to optimize model deployment processes and reduce latency.
• Monitor and troubleshoot inference systems, providing timely solutions to performance bottlenecks.
• Conduct performance testing and reliability assessments to ensure system robustness.
• Develop and maintain documentation for system designs, architectures, and processes.
• Stay up-to-date with the latest advancements in machine learning and distributed systems technology.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
• Proven experience in building and deploying machine learning models in production environments.
• Strong programming skills in Python, Java, or Scala.
• Experience with distributed computing frameworks such as TensorFlow, PyTorch, or Apache Spark.
• Solid understanding of cloud services (AWS, Google Cloud, Azure) and deployment architectures.
• Familiarity with containerization technologies (Docker, Kubernetes) is a plus.

Technologies & Tools

In this position, you will utilize a variety of artificial intelligence and machine learning frameworks, cloud computing platforms, and container orchestration tools. Specific technologies may include TensorFlow, PyTorch, AWS Sagemaker, Docker, and Kubernetes, along with version control systems like Git and CI/CD tools for continuous integration and deployment.

Ideal Candidates

The ideal candidates for the Distributed ML Systems Engineer - Inference role are those who possess a strong analytical mindset and an unwavering passion for machine learning and distributed systems. They should exhibit excellent problem-solving abilities, a collaborative spirit, and stellar communication skills, enabling them to work effectively in team settings. A candidate who stays abreast of the latest industry trends and methodologies, and who demonstrates a proactive approach to learning and innovation, would thrive in this dynamic environment.