Senior Engineer, AI

This position is responsible for helping to expand our capabilities in the intersection of traditional software development and artificial intelligence, focusing on building reliable systems that leverage state of the art language models and related technologies effectively. Also responsible for designing and implementing sophisticated retrieval systems, fine-tune models, develop robust prompting strategies, and create efficient smaller models for on premise deployment.

DUTIES AND RESPONSIBILITIES:

• Design and implement retrieval-augmented generation (RAG) systems with both semantic and traditional search capabilities
• Develop and optimize vector search systems for effective information retrieval
• Create data preparation pipelines for model fine-tuning
• Execute and evaluate model fine-tuning experiments
• Design and test prompt engineering strategies and in-context learning approaches
• Build fault-tolerant applications integrating with AWS Bedrock and SageMaker
• Implement production-grade Python backends for AI-powered features
• Develop evaluation frameworks for RAG and fine-tuning performance
• Design and implement knowledge distillation pipelines for smaller, deployable models
• Optimize models for on-premise deployment in data center environments
• Engineer reasoning capabilities in smaller self-hosted models
• Evaluate trade-offs between model size, performance, and reasoning capabilities
• Manage model deployment and monitoring in on-premise environments

EXPERIENCE AND QUALIFICATIONS:

• Bachelor’s degree in Computer Science or related field is required with a minimum of three years of relevant experience.
• Master’s degree with two years of relevant experience
• Ph.D. in relevant field with focus on machine learning, NLP, or related issues.
• Experience designing and implementing production AI systems, including:
• Prompt engineering and in-context learning
• Retrieval-augmented generation (RAG) systems
• Model fine-tuning and evaluation
• Knowledge distillation for deployment
• Production experience with Python and modern web frameworks
• Cloud platform experience, preferably AWS AI/ML services

KNOWLEDGE, SKILLS AND ABILITIES:

• Deep understanding of:
• LLM capabilities, limitations, and evaluation methodologies
• Vector databases and embedding systems
• On-premise model deployment considerations
• Demonstrated ability to:
• Design and optimize production-grade AI systems
• Apply systematic, data-driven approaches to experimentation and evaluation
• Balance technical constraints with business requirements
• Make sound technical decisions in complex situations
• Lead technical discussions and present solutions effectively
• Collaborate across engineering, research, and business teams
• Working knowledge of:
• Model optimization techniques
• Data center operations
• Infrastructure-as-code practices
• Demonstrated critical thinking and analytical skills, as well as the ability to handle complex situations and demonstrate sound judgment and problem-solving
• Excellent communication skills with the ability to organize, present, and articulate ideas both verbally and in writing
• Strong cross-functional collaboration skills
• Ability to balance model performance with resource constraints

Note: We are currently unable to hire candidates who require sponsorship or are on certain work visas (such as F1/OPT/CPT) for this position.