AI Inference Engineer

About Teton: Teton specializes in deploying cutting-edge AI technologies in healthcare settings, creating privacy-first solutions that improve patient monitoring and care delivery.

Role Overview: As an AI Inference Engineer at Teton, you’ll focus on optimizing and deploying machine learning models for real-time healthcare applications. You’ll ensure our AI systems perform reliably in production environments.

Key Responsibilities:

• Optimize ML models for low-latency inference
• Develop and maintain model serving infrastructure
• Collaborate with researchers to operationalize models
• Implement monitoring and versioning for deployed models
• Ensure model performance meets clinical requirements
• Stay current with inference optimization techniques

Required Skills:

• Experience with model optimization techniques
• Knowledge of hardware acceleration (GPU, TPU)
• Proficiency with model serving frameworks
• Understanding of quantization and pruning techniques
• Strong Python programming skills

Ideal Candidate:

• 3+ years of experience in ML inference
• Background in computer architecture preferred
• Experience with model compression techniques
• Familiarity with healthcare AI applications
• Ability to balance performance with resource constraints
• Passion for deploying impactful AI solutions