ZipRecruiter

Log In

1

Ml Inference Jobs in California (NOW HIRING)

E-Space

AI / Embedded ML Engineer

Saratoga, CA · On-site

$145K - $190K/yr

... inference latency • Use frameworks including TensorFlow Lite Micro, Edge Impulse, ONNX Runtime, and ExecuTorch • Integrate ML inference into embedded firmware written in C, C++, or Rust • ...

E-Space

AI / Embedded ML Engineer

Saratoga, CA · On-site

$145K - $190K/yr

  • Medical

  • PTO

... inference latency • Use frameworks including TensorFlow Lite Micro, Edge Impulse, ONNX Runtime, and ExecuTorch • Integrate ML inference into embedded firmware written in C, C++, or Rust • ...

E-Space

AI / Embedded ML Engineer

Saratoga, CA · Hybrid

$150K - $225K/yr

Software Embedding and Systems Integration ◦ Write clean, well-tested embedded software that integrates ML inference into real-time systems ◦ Work with RTOS environments such as FreeRTOS and ...

previous page

Showing results 41-60

All JobsMl Inference JobsMl Inference Jobs in California

Ml Inference information

What is ML inference?

ML inference refers to the process of using a trained machine learning model to make predictions or decisions based on new data. After a model has been trained on historical data, inference is the phase where that model is deployed and used in real-world applications, such as recognizing speech, detecting objects in images, or recommending products. The focus in ML inference is on speed, efficiency, and scalability to ensure quick predictions, often in real time. This process is critical for practical applications like mobile apps, web services, and embedded systems. Optimizing inference involves reducing latency, memory usage, and computational requirements.

What is the difference between Ml Inference vs Data Scientist?

AspectML InferenceData Scientist
Required CredentialsKnowledge of machine learning models, programming skillsDegree in data science, statistics, or related fields
Work EnvironmentDeploying models in production, real-time data processingData analysis, model development, research
Industry UsageAI product deployment, software companiesResearch institutions, tech firms, consulting

ML Inference focuses on deploying trained models to make predictions on new data, often in real-time. Data Scientists develop and analyze models, working primarily in research and development. While both roles require understanding of machine learning, ML Inference emphasizes deployment and operationalization, whereas Data Scientists focus on model creation and analysis.

What are some common challenges faced by ML inference engineers when deploying models to production?

ML Inference Engineers often encounter challenges such as optimizing model latency and throughput to meet production requirements, ensuring compatibility with diverse hardware environments, and managing model versioning and updates without disrupting service. Additionally, balancing resource utilization and inference accuracy while monitoring real-time performance metrics is crucial. Collaboration with data scientists, DevOps, and software engineers is typically essential to streamline deployment and maintain robust, scalable inference pipelines.

What are the key skills and qualifications needed to thrive in ML inference?

To thrive in ML Inference, you need a solid background in machine learning principles, programming (Python or C++), and experience with deploying models at scale, often supported by a degree in computer science or a related field. Familiarity with frameworks and tools such as TensorFlow, PyTorch, ONNX, and cloud platforms like AWS SageMaker or Google AI Platform is typically required. Strong problem-solving skills, attention to detail, and effective communication are crucial soft skills for collaborating with multidisciplinary teams and optimizing model performance. These skills ensure efficient, scalable, and reliable deployment of machine learning solutions in real-world applications.

Is ML inference a high paying job?

ML inference roles are generally well-paying, especially for those with skills in machine learning frameworks, programming, and cloud platforms. Salaries vary based on experience, location, and industry, but they tend to be higher than average for tech-related positions.

What are popular job titles related to Ml Inference jobs in California?

For Ml Inference jobs in California, the most frequently searched job titles are:

What job categories do people searching Ml Inference jobs in California look for?

The top searched job categories for Ml Inference jobs in California are:

What cities in California are hiring for Ml Inference jobs?

Cities in California with the most Ml Inference job openings:

Ml Inference jobs near you
Infographic showing various Ml Inference job openings in California as of August 2026, with employment types broken down into 90% Full Time, 4% Part Time, 2% Temporary, and 4% Contract. Highlights an 80% Physical, 6% Hybrid, and 14% Remote job distribution.

Member of Technical Staff, ML Systems

Netpreme

Santa Clara, CA • On-site

Full-time

Re-posted 24 days ago

Job description

Job Summary:
Netpreme is seeking a motivated LLM Systems Engineer to explore new and unconventional inference systems based on emerging hardware. The role involves prototyping various algorithms suitable for inference hardware and guiding the hardware team on product definition.
Responsibilities:
• Prototype and optimize emerging ML inference systems.
• Develop novel memory models for expandable vRAM.
• Write efficient GPU kernels for data movement.
• Perform design-space exploration, implementation, and benchmarking of inference engines, both in simulations and on real hardware.
Qualifications:
Required:
• MS or PhD in computer systems, ideally with a focus on LLM inference and/or distributed systems.
• Prior experience contributing to the core LLM inference infrastructures (vLLM, SGLang, TensorRT, etc.).
• Prior experience in accelerator programming (e.g. CUDA, JAX/Pallas, ROCm).
Preferred:
• Advanced computer architectures and performance engineering skills is a big plus.
Company:
Netpreme develops networked memory tiering technology that expands accelerator memory capacity for AI workloads. Founded in 2024, the company is headquartered in Cambridge, USA, with a team of 11-50 employees. The company is currently Early Stage.

Apply