Full Time

Software Engineer, Production Inference (Distributed Inference)

EngRadar
San Francisco, CA
$180,000 - $270,000* / year (about $87–$130 an hour)

Job Description

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

About this kind of role

What a Software Engineer, Production Inference (Distributed Inference) usually does. The employer's own details are in the listing.

Typically does: A Production Inference Software Engineer focuses on building, deploying, and maintaining systems that serve machine learning models in a production environment. This involves optimizing model performance, ensuring scalability and reliability, and monitoring system health. They work closely with machine learning engineers and DevOps teams to integrate models into real-time applications. Responsibilities often include troubleshooting issues, implementing automated testing, and improving the overall efficiency of the inference pipeline.

Tools and skills: Proficiency in programming languages like Python, experience with cloud platforms (e.g., AWS, Google Cloud, Azure), familiarity with containerization technologies (e.g., Docker, Kubernetes), and knowledge of machine learning frameworks (e.g., TensorFlow, PyTorch) are generally required.

Good fit for: Individuals with a strong background in software engineering and a passion for machine learning, particularly those who enjoy solving complex technical challenges related to performance and scalability, are typically successful in this role.

Not sure what kind of job to look for? Our career quiz is 30 quick questions, then the careers that fit your interests and what they pay. Take the career quiz →

View Similar Jobs

Matches Jobs

Similar jobs which you may be interested in. Typically using your existing skillset.