Production ML Engineer — LLMs, Agentic AI & Inference

INSPYR Solutions; Sunnyvale (CA); Hybrid; USD 120,000 - 180,000; Full time

Job summary

INSPYR Solutions is seeking a Machine Learning Engineer to join the Customer Systems team in a hybrid role based in Sunnyvale, CA or Austin, TX. You will design, develop, and optimize production-grade AI solutions focused on LLMs, agentic AI systems, and inference optimization.

You will evaluate model performance, run experiments, and implement techniques such as quantization to improve latency, throughput, and resource use.

Qualifications

• 3 years of AI/ML engineering experience with hands-on development.
• Experience deploying AI agents to production and knowledge of agentic AI architectures.
• Hands-on experience building and implementing RAG-based applications.
• Experience deploying and optimizing LLMs in production with open-source models.
• Proficiency in Python for ML development and testing.

Responsibilities

• Design, develop, test, and deploy AI agents and agentic workflows.
• Evaluate and optimize inference performance of open-source LLMs.
• Conduct performance benchmarking and experiments for model optimization.
• Implement inference optimization techniques, incl. quantization.
• Develop and enhance Retrieval-Augmented Generation (RAG) solutions.
• Research and evaluate emerging LLM architectures and frameworks.
• Collaborate with cross-functional teams to deploy and monitor production AI systems.

Skills

Python

AI/ML engineering

Production deployment

Benchmarking

Tools

RAG frameworks

Open-source LLMs

Job description

INSPYR Solutions is seeking a Machine Learning Engineer to join the Customer Systems team in a hybrid role based in Sunnyvale, CA or Austin, TX. You will design, develop, and optimize production-grade AI solutions focused on LLMs, agentic AI systems, and inference optimization.

You will evaluate model performance, run experiments, and implement techniques such as quantization to improve latency, throughput, and resource use.