Skip to main content

Senior Software Engineer - Full-Stack AI Applications

Posted 4 days ago

aramarkCoatesville (PA)

SENIORITY

Lead

Apply (opens in a new tab)

About the role

Senior Software Engineer - Full-Stack Ai Applications Our vision is to enable profitable growth to Aramark's Accounts by providing them with analytical assets that meet their needs as effectively and then efficiently as possible. To achieve this vision, Aramark will deliver strategic data assets that enable our operators to maximize the hospitality experience for our consumers and clients. We are seeking a Senior Software Engineer to join our team as a key technical contributor on the Document Intelligence Worker platform — a cloud-native, event-driven system that ingests, classifies, and processes documents at scale using AI agentic workflows. You will design and operate the pipelines and services that power automated document understanding and downstream analytics and AI-driven capabilities across Aramark, processing 1000+ documents per month for 12+ Lines of Business. You will work across Azure Blob Storage, Event Grid, Service Bus, Container Apps Jobs, AI Search, Cosmos DB, and Azure AI Foundry. This is a hybrid role based at our Philadelphia headquarters. Candidates must be local to the area or willing to relocate, and able to work onsite in a hybrid capacity.
Job Responsibilities: Design, build, and own components of the Document Intelligence Worker pipeline, including ingestion, classification, extraction, and downstream delivery to consumer applications, making design decisions that account for scalability, cost, and reliability. Architect and implement event-driven processing using Azure Blob Storage, Event Grid, and Service Bus, with Container Apps Jobs scaled via KEDA.Build and productionize AI agentic workflows using Azure AI Foundry — including orchestration, tool use, and multi-step reasoning over unstructured documents. Implement and maintain retrieval and indexing layers using Azure AI Search and Cosmos DB to support downstream search, analytics, and agentic retrieval. Design and build the application layer for agentic AI solutions — backend services and APIs (including authentication and orchestration between the UI and platform services) and React-based user interfaces such as chat, document review/approval tools, and agent monitoring dashboards. Own monitoring, observability, testing, and recovery mechanisms for production pipelines, including on-call support for critical incidents. Drive integration and synchronization work between source systems (on-premises and SaaS) and cloud-native platforms, working through dependencies across teams. Contribute to data engineering best practices — CI/CD for data and services, testing standards, and code and design review norms — and mentor junior and mid-level engineers and interns. Partner with product, engineering, and business stakeholders on technical trade-offs, feasibility, and cost, translating requirements into reliable, scalable data and AI services and explaining complex AI and data concepts to non-technical audiences. Evaluate and prototype emerging document intelligence and agentic AI techniques, and recommend their adoption where they add measurable value, weighing cost and risk.
Qualifications: BS or MS in Computer Science, Data Engineering, Data Science, or a related field, with 8+ years (or 6+ with an MS) of professional experience across data engineering and software development (including full-stack development with backend services), including 3+ years of hands-on experience building applied AI, machine learning, or data science solutions, with production experience building LLM-powered and AI agentic applications, plus experience in document intelligence (OCR, IDP, document classification/extraction).This includes: Full-stack development experience, including backend services and API design (e.g., REST, authentication/authorization, service-to-service integration) and React frontend development, sufficient to build UIs for agentic AI applications (e.g., chat interfaces, document review/approval tools, agent monitoring dashboards). Strong proficiency in Python and SQL, with production experience building and operating data or AI services. Hands-on experience with a major cloud platform (Azure, AWS, or GCP), including object storage, event-driven messaging, and container orchestration with autoscaling. Experience with Azure services (Blob Storage, Event Grid, Service Bus, Container Apps, KEDA) is preferred. Experience building or integrating AI agentic workflows and LLM-enabled applications — e.g., via Azure AI Foundry, AWS Bedrock, Vertex AI, LangChain, Semantic Kernel, AutoGen, or comparable frameworks. Experience with document intelligence / intelligent document processing tooling (e.g., Azure Document Intelligence, AWS Textract, Google Document AI, OCR pipelines, layout- or vision-based extraction models). Experience with vector search and retrieval-augmented generation, including Azure AI Search or equivalent (e.g., Elasticsearch, Pinecone, Weaviate). Experience with NoSQL/document databases such as Cosmos DB, DynamoDB, or Firestore, and designing data models for high-throughput, low-latency workloads. Solid grounding in CI/CD practices, version control (Git), automated testing, and production monitoring/observability. Comfortable working across distributed teams, with a track record of working with both engineers and non-technical business stakeholders and adapting communication to the audience.

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.

More like this