AI Software Engineer (GenAI/RAG/Azure AI Foundry) - REMOTE

The Phia Group
United States
25 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Job source

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Application Integration Architecture Application Services Microsoft Azure Cloud Engineering Code Generation Software Quality Software Debugging DevOps Python (Programming Language) Microsoft SQL Server
+28 more
Node.Js NoSQL Performance Tuning Azure Machine Learning Software Deployment Software Engineering SQL Databases Web Application Frameworks Enterprise Software Applications Chatbots Retrieval-Augmented Generation Large Language Models Multi-Agent Systems Prompt Engineering Spring-boot Generative AI Backend Fastapi AI Platforms AngularJS Kubernetes Information Technology Azure AKS Front End Software Development Cloud Integration GPT Api Management Docker

Job description

We are seeking a forward-thinking AI Software Engineer to design, build, and scale intelligent applications powered by modern AI technologies. This role goes beyond traditional software engineering - focusing on Generative AI, Retrieval-Augmented Generation (RAG), and AI-assisted development using tools like Claude, GPT, and other LLM platforms.

You will play a key role in shaping our AI roadmap by building production-grade AI systems, optimizing developer productivity with AI tools, and integrating intelligent workflows into our healthcare platforms., AI Engineering & GenAI Development

  • Design and implement RAG (Retrieval-Augmented Generation) pipelines using modern vector databases and embeddings.
  • Build and optimize LLM-powered applications (chatbots, copilots, automation agents).
  • Leverage tools like Claude, GPT, and AI coding assistants to accelerate development and improve code quality.
  • Develop agentic AI workflows using frameworks that enable reasoning, tool usage, and multi-step decision-making.
  • Design and orchestrate multi-agent workflows including orchestrator/supervisor patterns, agent handoffs, and tool routing

Azure AI & Cloud Integration

  • Architect and deploy AI solutions using Azure AI Foundry / Azure OpenAI / Azure ML.
  • Manage scalable deployments using Azure Kubernetes Service (AKS), Docker, and Helm.
  • Implement semantic search and vector indexing using tools like Qdrant or Azure Cognitive Search.
  • Build model-agnostic AI routing layers ( this is to abstract the LLM provider dependencies and create pipelines where we can change models on the fly)

Full-Stack + AI Integration

  • Build and maintain full-stack applications integrating AI services:
  • Frontend: Angular / modern JS frameworks
  • Backend: FastAPI, Spring Boot, Node.js
  • Data: SQL/NoSQL systems
  • Integrate AI services into existing enterprise systems and APIs.

AI-Driven Development & Productivity

  • Use AI tools (Claude, Copilot, etc.) for:
  • Code generation and refactoring
  • Debugging and optimization
  • Test generation and documentation
  • Continuously evaluate and adopt new AI tools to improve engineering velocity.

DevOps & Scalability

  • Build and maintain CI/CD pipelines (Azure DevOps) for AI applications.
  • Optimize system performance, scalability, and reliability of AI workloads.
  • Monitor and improve model performance, latency, and cost efficiency., This job description is not intended to be and should not be construed as an all-inclusive list of all the responsibilities, skills or working conditions associated with the position. While it is intended to accurately reflect the position activities and requirements, the company reserves the right to modify, add or remove duties and assign other duties as necessary.

Requirements

  • Bachelor’s degree in Computer Science, IT, or related field + relevant experience.
  • Strong experience with:
  • Python (FastAPI preferred)
  • Modern backend or full-stack frameworks
  • Hands-on experience with:
  • RAG architecture, embeddings, and vector databases
  • LLMs (GPT, Claude, or similar)
  • Experience deploying applications on Azure (AKS, Azure AI services).
  • Familiarity with Docker, Kubernetes, and cloud-native architectures.
  • Experience with MS SQL, Azure storage, Azure App services, APIM.

Preferred Qualifications

  • Experience with Azure AI Foundry or similar GenAI platforms.
  • Strong understanding of:
  • Prompt engineering
  • Context management in LLMs
  • Fine-tuning / evaluation techniques
  • Experience with vector DBs like Qdrant, Pinecone, or Azure Cognitive Search.
  • Exposure to agent frameworks (LangChain, Semantic Kernel, AutoGen, etc.).
  • Prior experience building AI copilots or internal AI tools.

Working Conditions / Physical Demands Sitting at workstation for prolong periods of time. Extensive computer work. Workstation may be exposed to overhead fluorescent lighting and air conditioning. Fast paced work environment. Operates office equipment including personal computer, copiers, and fax machines.

About the company

The Phia Group is a service- oriented organization assisting employee health plans nationwide. We provide our clients with innovative cost-cutting solutions and constantly expanding service offerings. We continue to enjoy growth thanks to our most valuable resource - our talented and committed team.

At The Phia Group, whose mission is to provide high quality yet affordable healthcare to American employees and their families, you can look forward to not only unparalleled benefits for yourself but also being immersed in a company that was named one of USA Today’s Top Workplaces for 2025. Meanwhile, from a regional perspective, both The Boston Globe and Louisville Business First also recognized our unwavering commitment to upholding an internal culture of inclusivity, enjoyment, and empathy for our valued employees by listing The Phia Group in their respective lists for the Top Places to Work in 2025.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:14 min

Exploring internal AI product initiatives and global engineering roles

Maria Apazoglou · Coffee With Developers

40 sec

Generative pre-trained transformer models powering code completions

lgonta lgonta +1 · WWC 2024

2:37 min

Comparing traditional SQL tables versus NoSQL non-tabular databases

Stanimira Vlaeva · JS Congress

2:07 min

Inspecting default bridge architectures and custom Docker networks

Oliver Seitz Oliver Seitz · WWC 2025

2:18 min

Redefining developer roles and software architecture requirements

Laurie Voss · Coffee With Developers

51 sec

Assessing GPT-4o performance for pull request feedback

Merrill Lutsky Merrill Lutsky · WWC 2025

Videos

See all

Related articles

See all