Ai Engineer

Heitmeyer Consulting; Columbus (OH); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Heitmeyer Consulting seeks an AI Engineer to design, build, and scale an enterprise AI platform powering credit memo review. You will orchestrate LLM interactions, manage prompts, and implement RAG-based workflows integrated with secure APIs.

You will develop data pipelines, ensure governance, and collaborate with data scientists and software engineers to operationalize ML models and provide transparent, auditable AI solutions across cloud-native architectures.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related discipline.
• 7+ years of software engineering, AI engineering, or machine learning engineering experience.
• Strong experience building cloud-native applications in AWS.
• Experience with AWS services including Glue, Athena, and related analytics technologies.
• Experience building data pipelines and distributed processing solutions.
• Experience integrating Large Language Models into enterprise applications.
• Experience with Retrieval Augmented Generation (RAG).
• Experience developing REST APIs and microservices.
• Experience with SQL and modern data engineering practices.
• Understanding of software architecture, CI/CD, DevOps, and Infrastructure as Code.

Responsibilities

• Design, build, and support the enterprise AI platform that powers an intelligent credit memo review solution.
• Develop scalable, cloud-native AI services that orchestrate large language model (LLM) interactions, prompt management, Retrieval Augmented Generation (RAG), structured output generation, and citation creation.
• Build secure APIs and automated data pipelines that ingest, process, and transform structured and unstructured data for AI-driven workflows.
• Integrate AI capabilities into enterprise applications while partnering with Data Scientists to operationalize machine learning models and LLMs.
• Develop workflow capabilities that support user interaction, reviewer feedback capture, resolution management, tagging operations, and audit trail management.
• Build and manage high-quality data assets, including evaluation datasets, training datasets, and curated data used to improve AI model performance.
• Implement enterprise governance capabilities including authentication, authorization, logging, monitoring, version control, data lineage, retention management, and model traceability.
• Ensure AI solutions meet security, regulatory, compliance, and Model Risk Management requirements while maintaining transparency and explainability.
• Continuously evaluate and implement emerging AWS AI services and modern data technologies to improve platform performance and scalability.
• Automate manual business processes by delivering reliable, production-ready AI solutions that improve operational efficiency and enable future AI innovation.

Skills

AWS cloud

LLM integration

RAG

Data pipelines

REST APIs

CI/CD

Infrastructure as Code

Security & governance

Model risk management

Prompt engineering

Education

Bachelor's degree in Computer Science / Software Engineering / Information Systems

Tools

AWS Glue

AWS Athena

Databricks

Apache Airflow

Shakudo

Vector databases

Semantic search

Job description

Must sit in the following locations - Columbus, OH; Chicago, IL; Minneapolis, MN; Detroit, MI; Charlotte, NC; or Dallas, TX.

Heitmeyer Consulting is currently seeking an AI Engineer to design, build, and scale the AI platform supporting the next generation of commercial credit review capabilities. This role will focus on developing the AI orchestration layer, integrating large language models, automating data pipelines, and building cloud-native AI services that enable secure, governed AI solutions.

The ideal candidate has strong experience with AWS cloud technologies, AI infrastructure, data engineering, and modern machine learning platforms. This individual will work closely with Data Scientists, Product Owners, Risk teams, and Software Engineers to build production-ready AI capabilities that support commercial credit memo review while meeting enterprise governance standards.

Key Responsibilities:

• Design, build, and support the enterprise AI platform that powers an intelligent credit memo review solution.
• Develop scalable, cloud-native AI services that orchestrate large language model (LLM) interactions, prompt management, Retrieval Augmented Generation (RAG), structured output generation, and citation creation.
• Build secure APIs and automated data pipelines that ingest, process, and transform structured and unstructured data for AI-driven workflows.
• Integrate AI capabilities into enterprise applications while partnering with Data Scientists to operationalize machine learning models and LLMs.
• Develop workflow capabilities that support user interaction, reviewer feedback capture, resolution management, tagging operations, and audit trail management.
• Build and manage high-quality data assets, including evaluation datasets, training datasets, and curated data used to improve AI model performance.
• Implement enterprise governance capabilities including authentication, authorization, logging, monitoring, version control, data lineage, retention management, and model traceability.
• Ensure AI solutions meet security, regulatory, compliance, and Model Risk Management requirements while maintaining transparency and explainability.
• Continuously evaluate and implement emerging AWS AI services and modern data technologies to improve platform performance and scalability.
• Automate manual business processes by delivering reliable, production-ready AI solutions that improve operational efficiency and enable future AI innovation.

Required Skills:

• Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related discipline.
• 7+ years of software engineering, AI engineering, or machine learning engineering experience.
• Strong experience building cloud-native applications in AWS.
• Experience with AWS services including Glue, Athena, and related analytics technologies.
• Experience building data pipelines and distributed processing solutions.
• Experience integrating Large Language Models into enterprise applications.
• Experience with Retrieval Augmented Generation (RAG).
• Experience developing REST APIs and microservices.
• Experience with SQL and modern data engineering practices.
• Understanding of software architecture, CI/CD, DevOps, and Infrastructure as Code.

Preferred Skills:

• Experience with Databricks.
• Experience with Apache Airflow.
• Experience with Shakudo or similar AI orchestration platforms.
• Experience with vector databases and semantic search.
• Experience with prompt engineering and LLM evaluation.
• Experience within banking, commercial lending, or financial services.
• Familiarity with responsible AI, governance, explainability, and audit requirements.