Design, test, and refine prompts to optimize LLM outputs for accuracy, relevance, and tone across diverse use cases.
Train and fine-tune LLMs using proprietary datasets and prompt engineering techniques.
Embed AI prompts into applications and software to automate complex or repetitive tasks.
Monitor performance data to optimize outputs and fine tune strategies.
Support the integration of AI-powered chatbots into team workflows and enterprise platforms.
Monitor AI system performance, analyze output quality, and iterate based on feedback and metrics.
Measure SEO and adjust strategies to improve performance on key terms.
Collaborate with domain subject matter experts, product, engineering, and UX teams to align AI behavior with user expectations and business goals.
Maintain documentation of prompt libraries, model behaviors, and integration strategies.

Bachelor’s degree in Computer Science, AI/ML, Computational Linguistics, or related field.
2+ years of experience in prompt engineering, LLM fine-tuning, or NLP model development.
Experience with Retrieval-Augmented Generation (RAG) using Amazon Kendra or OpenSearch.
Familiarity with vector databases and embedding models hosted on AWS.
Knowledge of IAM roles, security best practices, and cost optimization in AWS environments.
Experience integrating AI into CI/CD pipelines using AWS CodePipeline or CodeBuild.
Demonstrated experience (1-3 years) providing technical assistance to federal partners.
Hands-on experience with Amazon SageMaker, Amazon Bedrock, and AWS Glue.
Proficiency in Python and experience with AI/ML libraries.
Familiarity with deploying serverless applications using AWS Lambda and Step Functions.
Experience with chatbot development using Amazon Lex or similar frameworks.
Strong understanding of prompt evaluation, model behavior tuning, SEO, and web performance metrics (GA4).

AI Solutions Specialist

Key skills