Software AI Engineer Mid-Level, Context Engineering

WEX is a company focused on AI and context infrastructure, and they are seeking a Software AI Engineer to build and maintain core software components. The role involves developing features for the AI Data Lakehouse, automating CI/CD pipelines, and ensuring platform reliability through operational excellence.

Responsibilities:

• Feature Development: Implement and maintain core services for the AI Data Lakehouse, focusing on efficient data retrieval and storage optimizations for AI workflows
• Pipeline Automation: Build and support CI/CD pipelines to automate the deployment of AI models, prompt templates, and infrastructure updates
• Agentic Support: Develop and test tool-execution environments and API interfaces that allow AI agents to interact with internal business systems safely
• Operational Excellence: Participate in on-call rotations and troubleshooting to ensure platform reliability. Write unit tests, integration tests, and documentation for new features
• Context Retrieval: Work on the "Context Fabric" to implement search and retrieval patterns (like RAG) that help agents access secure enterprise data
• Cloud Management: Assist in managing cloud resources across AWS and Azure, ensuring environments are cost-effective and secure

Requirements:

• 3+ years of professional software development experience
• Strong proficiency in Python and either Java or Scala. You write clean, maintainable, and well-documented code
• Experience building and consuming RESTful APIs or gRPC services
• Understanding of relational databases (Postgres/MySQL) and familiarity with how data is stored in a distributed environment
• Hands-on experience navigating the AWS or Azure Management Consoles. You should be comfortable managing basic services like IAM, S3/Blob, and compute instances
• Basic experience with Terraform. You can read, modify, and deploy infrastructure modules
• Familiarity with GitHub Actions, GitLab CI, or Jenkins. You understand how to automate the build-test-deploy lifecycle
• Basic experience with monitoring tools like Prometheus, Grafana, or cloud-native solutions (CloudWatch/Azure Monitor)
• Familiarity with LLM concepts and frameworks like LangChain or LlamaIndex. You've experimented with or built basic RAG-based applications
• A desire to learn and implement new standards like the Model Context Protocol (MCP)
• Interest in how autonomous agents function, including tool-use (function calling) and state management
• Basic understanding of vector databases (e.g., Pinecone, Milvus) and how search impacts AI performance
• Ability to work effectively in an agile environment, participating in sprint planning and daily stand-ups
• A strong desire to stay current with the rapidly changing AI and cloud landscape
• Bachelor's degree in Computer Science, Software Engineering, or a related technical field