Senior AI Engineer

Build production-ready AI with eimagine in Indianapolis, IN (remote). In this role, you’ll design, build, and deploy AI applications that improve business processes, support trusted access to information, and enable better decision-making. The work blends analytical and LLM model capabilities with application engineering, evaluation, monitoring, and knowledge transfer so solutions can be maintained and scaled.

What you’ll do

• Develop AI application services, APIs, and integrations connecting approved models, enterprise data, and business workflows.
• Implement reusable tools and Model Context Protocol (MCP) services within established architecture and security standards.
• Create retrieval-augmented generation (RAG), search, and guided assistance capabilities using approved content, source references, permission-aware retrieval, and appropriate human escalation.
• Build and maintain ingestion and retrieval pipelines, including document parsing, chunking, metadata enrichment, embeddings, and indexing.
• Keep source content current and ensure access permissions remain accurate across the pipeline.
• Partner with data engineering and analytics teams to assess data readiness and prepare reproducible datasets and features for AI and predictive applications.
• Evaluate predictive models with analytics specialists for real business use cases.
• Implement reproducible scoring, integrate model outputs into applications, and monitor performance.
• Apply additional machine learning approaches when appropriate to the use case and available expertise.
• Translate model outputs into understandable explanations, prioritized work queues, and scenario tools.
• Work with business stakeholders to connect recommendations to practical actions and measure results.
• Add automated tests and evaluations for answer quality, model performance, access controls, and failure cases.
• Version code, prompts, datasets, and models; monitor quality, reliability, latency, and operating cost.
• Apply approved privacy, security, and responsible AI requirements including least-privilege access, auditability, subgroup performance review, and human review of consequential recommendations.
• Implement AI safeguards such as prompt injection defenses, input and output validation, content filtering, secure tool and API invocation, and protection of sensitive data in prompts, logs, and responses.
• Document assumptions, limitations, operating procedures, and technical decisions.
• Support knowledge transfer so client and internal teams can maintain and extend solutions.
• Deliver tested, maintainable AI services, reproducible analyses and evaluations, documented data and model limitations, workflow-ready integrations, and practical operating guidance.
• Establish release criteria with the team and demonstrate business value before scaling a capability.

What you bring

• Demonstrated experience delivering production software and AI or machine learning capabilities, including responsibility for deployment, troubleshooting, and continuous improvement.
• Python and SQL skills, API development experience, and solid software engineering practices including Git, automated testing, code review, and deployment pipelines.
• Hands-on experience building LLM applications using retrieval, tool calling, structured outputs, and systematic evaluation.
• Ability to determine when a simpler search, workflow, or rules-based solution is appropriate.
• Practical knowledge of LLM security risks including prompt injection, data leakage, and unsafe tool use, with experience implementing mitigations.
• Working knowledge of predictive modeling and machine learning, including integrating model outputs into software or operational workflows.
• Ability to collaborate with an experienced modeler on evaluation and production readiness.
• Understanding of model validation and risks such as data leakage, missing data, class imbalance, and uncertainty.
• Ability to implement reliable scoring using the same feature definitions and transformations from model development.
• Capability to select evaluation measures aligned to operational needs, including precision and recall, probability calibration, and performance across relevant user groups or business segments.
• Understanding of the difference between prediction and evidence that an action causes improvement.
• Experience deploying cloud-based services, including authentication, authorization, secrets, logging, and monitoring.
• Ability to work in an Azure-based environment.
• Clear communication with technical and business stakeholders, comfort with evolving requirements, and the ability to identify when specialist support is needed.
• Experience with Azure AI Foundry, Azure AI Search, FastAPI, Azure Web Apps or Container Apps, and Microsoft Entra ID (or closely comparable technologies).
• Experience consuming governed Snowflake datasets; MCP services; knowledge graphs or semantic layers; and React / TypeScript integration.
• Experience delivering enterprise solutions involving sensitive data, complex workflows, or human decision support.
• Hands-on supervised machine learning development on structured data, plus familiarity with model lifecycle operations, explainability, experimental design, causal inference, or constrained optimization.

Education

Bachelor’s degree in information technology, computer science, or equivalent job-related experience is required.

Technologies

• Python, SQL, Git
• FastAPI
• Azure Web Apps, Container Apps, Azure AI Foundry, Azure AI Search
• Microsoft Entra ID, Azure
• Snowflake, React, TypeScript
• Model Context Protocol (MCP)
• Retrieval-augmented generation (RAG)