Sr AI & Software Engineer

Rōnin Consulting; Nashville (TN); On-site; USD 130,000 - 190,000; Full time

Job summary

Rōnin Consulting in Nashville, TN, seeks a Sr AI & Software Engineer to design and deliver production-grade Generative AI solutions for a Fortune 500 healthcare client. This is a 9-month contract-to-hire engagement with a clear path to permanent placement.

You will architect RAG systems, grounding pipelines, and vector-store infrastructure on enterprise cloud platforms, with strong emphasis on production delivery and compliance.

Qualifications

• 8+ years of software engineering experience with AI/ML delivery.
• Production delivery of Generative AI applications at enterprise scale.
• Hands-on experience with an enterprise AI platform (GCP Vertex AI/Gemini, AWS Bedrock/SageMaker, or Azure AI Foundry/Azure OpenAI).
• Deep experience designing and building RAG architectures in production.
• Experience with vector stores and embedding pipelines.

Responsibilities

• Lead the design, development, and deployment of scalable, production-grade Generative AI solutions on enterprise cloud platforms.
• Architect and build retrieval-augmented generation (RAG) systems grounding LLMs in domain data.
• Design data pipelines for embedding data into vector stores and ensure governance/compliance.

Skills

AI/ML delivery

Production-grade engineering

Leadership

Agile practices

Education

Bachelor's degree in Computer Science or related field

Tools

Docker/Kubernetes

LangChain

LangGraph

Google ADK

CrewAI

MLOps

Job description

Nashville, TN (On-site / Local Candidates Only)

Contract-to-Hire | 9-Month Engagement

AI Transformation, Integration & Hybrid Cloud

About The Role

Join an elite innovation team at Rōnin Consulting where AI engineering and full-stack software development converge. This is a contract-to-hire engagement — a 9-month contract with a clear path to permanent placement for the right candidate.

As a Sr AI & Software Engineer based in Nashville, TN, you will provide technical leadership designing and delivering production-grade Generative AI solutions for a Fortune 500 healthcare client with a nationwide footprint.

This role demands real production delivery — not POCs, not demos. You will architect Retrieval-Augmented Generation (RAG) systems, agentic workflows, grounding pipelines, and vector store infrastructure, and integrate them into enterprise-grade full-stack applications. The client’s AI stack is centered on enterprise cloud AI platforms — GCP Vertex AI and Gemini are the primary environment, but engineers with equivalent depth on AWS (Bedrock, SageMaker) or Azure (AI Foundry, Azure OpenAI) are strongly encouraged to apply. Cloud platform depth matters more than which hyperscaler is on your resume.

This is a role for a senior engineer with 8+ years of experience who thrives at the frontier of AI innovation: equally comfortable designing a vector store schema, building a grounding pipeline, writing a clean API, and translating complex AI concepts for non-technical healthcare stakeholders. Prior healthcare or regulated-domain experience is a meaningful advantage with this client.

Responsibilities

Generative AI & Agentic Systems

• Lead the design, development, and deployment of scalable, production-grade Generative AI solutions on enterprise cloud platforms (GCP Vertex AI / Gemini, AWS Bedrock / SageMaker, or Azure AI Foundry / Azure OpenAI)
• Architect and build sophisticated Retrieval-Augmented Generation (RAG) systems that ground LLMs in proprietary and domain-specific data, ensuring response accuracy and factual reliability in regulated healthcare contexts
• Design and implement efficient data pipelines for preparing, processing, and embedding data into vector stores, with attention to data governance and compliance requirements
• Develop grounding strategies and design the data structures needed to connect LLMs with enterprise and real-time information sources
• Design and implement agentic AI systems capable of complex reasoning, multi-step task execution, and autonomous operation using frameworks such as LangChain, LangGraph, Google ADK, or custom orchestration
• Integrate the Model Context Protocol (MCP) to standardize LLM-to-tool communication and enhance system interoperability where applicable
• Build and deploy evaluation frameworks, guardrails, and monitoring to ensure model reliability and safety in production
• Perform proof-of-concept and proof-of-technology work to secure stakeholder buy-in for new AI initiatives

Full-Stack Software Engineering

• Design client-side and server-side architecture with clearly defined AI integration points and attention to security and data protection in healthcare environments
• Build enterprise-grade applications in your language of strength (Python, Java, Node.js, C#, or similar), including APIs, services, and integrations with AI endpoints and third-party platforms
• Develop and manage robust SQL and NoSQL databases and application layers, including reusable data objects and automated testing frameworks
• Work with Docker/Kubernetes, serverless, and microservice architectures in cloud-native environments
• Implement security, data protection, and compliance controls appropriate to healthcare and enterprise environments
• Partner with data scientists and AI engineers to optimize intelligent features, pipeline performance, and system reliability

Leadership & Collaboration

• Explain complex AI architectures and trade-offs clearly to non-technical and mixed business/technical stakeholders in a healthcare enterprise context
• Provide technical mentorship and foster a collaborative, growth-oriented team environment
• Lead investigations and solution proposals for complex engineering and design challenges in the AI domain
• Guide team members in scope-of-work estimation and forecasting for AI-related projects
• Collaborate with business stakeholders, product owners, and clinical or operational teams to capture functional and non-functional requirements
• Drive delivery using Agile practices and principles; write clear technical documentation for systems, APIs, and AI workflows

Requirements & Skills

Skill / Experience Level 8+ years of software engineering experience with demonstrated progression into AI/ML delivery

Required Production delivery of Generative AI applications at enterprise scale — not just POCs or prototypes

Required Hands-on experience with an enterprise AI platform: GCP Vertex AI / Gemini, AWS Bedrock / SageMaker, or Azure AI Foundry / Azure OpenAI

Required Deep experience designing and building RAG (Retrieval-Augmented Generation) architectures in production

Required Proven experience with vector stores and embedding pipeline design (e.g., Vertex AI Vector Search, Pinecone, OpenSearch, Azure AI Search)

Required Hands-on experience building data pipelines for embedding, grounding, and connecting LLMs with enterprise data sources

Required Cloud-native development: serverless, container-based (Docker/Kubernetes), or microservice architectures on at least one major hyperscaler

Required Full-stack proficiency in 4+ of: Python, Java, C#, Node.js, SQL/NoSQL databases, ETL/data pipelines, message queues/event streaming, Docker/Kubernetes, microservices

Required Experience with agentic / multi-agent workflow frameworks (LangChain, LangGraph, Google ADK, CrewAI, or custom orchestration)

Required DevOps and CI/CD experience: GitHub Actions, Azure DevOps, Jenkins, Terraform, or equivalent; MLOps / model deployment pipelines a strong plus

Required Demonstrated ability to explain complex AI systems clearly to non-technical and mixed business/technical stakeholders

Required Experience integrating with EMR/EHR, CRM, ERP, or eCommerce systems and common enterprise integration patterns

Required Strong understanding of Agile methodology and software development lifecycles

Required Local to Nashville, TN — on-site availability required

Required GCP Vertex AI / Gemini depth: Vertex AI Studio, Vertex AI Pipelines, AI Agent Builder, Cloud Run, Dataflow, Pub/Sub, BigQuery

Preferred Healthcare or regulated-domain experience: HIPAA-adjacent systems, EMR/EHR workflows, clinical data, or HL7/FHIR integration

Preferred Knowledge of the Model Context Protocol (MCP) and experience implementing MCP-based LLM-to-tool integrations

Preferred Experience with LLM evaluation frameworks, guardrails, and AI safety practices for regulated environments

Preferred Experience with .NET Core / C# in enterprise application contexts

Preferred Familiarity with prompt engineering patterns, chain-of-thought orchestration, and output evaluation techniques

What We're Looking For

• Growth mindset and genuine curiosity in the rapidly evolving field of AI
• Adaptability and comfort navigating diverse technical ecosystems and ambiguous problem spaces
• Strong organization skills and great attention to detail
• Collaborative spirit with the ability to work independently and lead a team toward specific outcomes
• Ability to lead community events and internal knowledge-sharing focused on software development and delivery
• Strong understanding of codebase context and its relationship to broader business objectives

Education

Bachelor's degree in Computer Science, Software Engineering, Statistics, or a relevant technical field. Equivalent practical experience with a strong portfolio of AI and software engineering work will be considered.

Why Rōnin Consulting

• Competitive contract compensation with a structured path to full-time placement
• Contract-to-hire structure: 9-month engagement with conversion for the right candidate
• Collaborative, close-knit team of AI and engineering specialists in Nashville
• Leadership committed to technical excellence and quality delivery
• Opportunity to work at the absolute forefront of GCP-native AI development
• Diverse client portfolio spanning healthcare, finance, government, and enterprise