Ai Application Engineer

Summary

Join Sidecar Health, a company redefining health insurance, as an AI Application Engineer. You will optimize and refine large language model (LLM) interactions within a serverless AWS environment. This role demands expertise in designing and deploying scalable AI applications using various AWS services. You will develop and maintain prompt automation pipelines, explore prompt strategies to enhance AI model responses, and conduct performance monitoring. The ideal candidate possesses a strong background in software engineering, AI, and AWS serverless architecture. Sidecar Health offers a competitive salary, benefits, and the opportunity to impact healthcare transformation.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Information Systems, Business Administration, or a related field
• 4+ years of professional experience in software engineering, with a focus on AI or machine learning platforms
• Fluency in AWS serverless architecture, including Lambda, API Gateway, Step Functions, S3, DynamoDB, and IAM
• Strong TypeScript programming skills
• Hands-on experience with AI APIs such as OpenAI, Anthropic, and Hugging Face
• Understanding of LLM behavior and prompt engineering techniques, including model biases, tokenization, embeddings, and response optimization
• Cloud-native development expertise, including deploying and scaling AI applications in AWS
• Experience with infrastructure as code (IaC) using AWS SAM, AWS CDK, Serverless framework, or CloudFormation
• Familiarity with monitoring and logging tools such as AWS CloudWatch, X-Ray, or Datadog
• Ability to troubleshoot performance bottlenecks in serverless environments and optimize for cost-efficiency

Responsibilities

• Develop, optimize, and refine AI-generated outputs through advanced prompt engineering techniques
• Design agentic systems leveraging AWS Step Functions and Amazon Bedrock
• Design and implement serverless workflows to support AI-driven applications using AWS Lambda, API Gateway, and DynamoDB
• Build and maintain scalable prompt automation pipelines using AWS services
• Explore prompt strategies to enhance AI model responses and mitigate inconsistencies or hallucinations
• Conduct performance monitoring, logging, and error handling for AI-related API calls and workflows in AWS
• Stay updated on advancements in AI, LLMs, and cloud computing, applying new techniques to improve model performance
• Develop documentation, best practices, and internal tooling for prompt engineering within a serverless ecosystem

Benefits

• Competitive salary, bonus opportunity, and equity package
• Comprehensive Medical, Dental, and Vision benefits
• A 401k retirement plan
• Paid vacation and company holidays
• Opportunity to make an impact at a rapidly growing mission-driven company transforming healthcare in the U.S