Role : Sr. Gen AI Data Engineer
Location : Chicago, IL
Experience : 9+ years
United's Digital Technology team designs, develops, and maintains massively scaling technology solutions brought to life with innovative architectures, data analytics, digital solutions, and practical AI-enabled capabilities.
The Notifications team enables enterprise communication capabilities supporting customer and crew portfolios. This contractor role will focus on hands-on design, development, modernization, and production delivery of notification platform services, integrations, event-driven capabilities, and AI-enabled communication use cases.
Key Responsibilities :-
The role of Senior Developer will have a technical focus on enabling Notifications at the enterprise level and supporting a robust communication platform for customer and crew portfolios. This is a hands-on senior individual contributor role. This is not a management role. The expectation is to actively design, code, debug, optimize, deploy, and support production-grade solutions.
Design AND implement core services for the enterprise Notifications platform, including APIs, event-driven integrations, orchestration components, templates, and platform capabilities.
Write, review, debug, and optimize production code actively; lead through hands-on engineering contribution rather than delegation.
Build cloud-native backend services using Java, Spring Boot, Apache Camel, microservices, container technologies, and AWS services.
Develop and integrate AI/GenAI capabilities hands-on, including prompt design, LLM integration, RAG pipelines, embeddings/vector search, semantic search, classification, summarization, and AI-assisted communication workflows.
Prototype, validate, and productionize AI-enabled features while considering latency, accuracy, cost, monitoring, fallback design, and operational reliability.
Design solutions for high availability, scalability, resiliency, observability, performance, security, privacy, and compliance needs.
Support integrations with internal enterprise systems, eventing platforms, data providers, communication providers, and vendor-managed services as needed.
Troubleshoot and resolve complex production issues directly, including performance bottlenecks, integration failures, data issues, and system reliability concerns.
Work closely with architects, product owners, business stakeholders, development teams, and vendor teams to convert requirements into working solutions.
Contribute to technical design, system documentation, code reviews, automated testing, CI/CD pipelines, release readiness, and production support practices.
Ensure solutions are aligned with enterprise engineering standards, security expectations, and application lifecycle best practices.
Mentor developers through code-level guidance, design reviews, and engineering best practices; however, the primary expectation remains hands-on delivery.
Qualifications -
Bachelor's degree in Computer Science, Information Systems, Engineering, related field, or equivalent work experience required.
Minimum 8 years of overall experience in software engineering, application development, integration, and SDLC delivery.
Strong recent hands-on software development experience; candidate must be comfortable spending majority of time coding, debugging, designing, and delivering working software.
Minimum 8 years of hands-on Java backend development experience, including Spring Boot, REST APIs, microservices, and open-source technologies.
Minimum 3 years of hands-on experience with event-driven systems, messaging, streaming, integration, or notification platform capabilities.
Hands-on experience with Apache Camel or equivalent enterprise integration frameworks.
Minimum 4 years of hands-on experience with AWS or equivalent cloud services such as EC2, S3, RDS, VPC, CloudFront, Lambda, EKS, ECS, API Gateway, DynamoDB, DocumentDB, AmazonMQ, or related services.
Strong hands-on AI/GenAI implementation experience in enterprise or production-grade applications; AI experience should not be limited to strategy, vendor discussions, or conceptual understanding.
Practical experience involves personally implementing one or more AI capabilities such as LLM integration, prompt engineering, RAG, embeddings/vector search, semantic search, classification, summarization, AI-assisted workflow automation, or decision-support capabilities.
Understanding responsible AI and secure AI engineering practices, including data privacy, access control, guardrails, evaluation, monitoring, hallucination risk, human review where needed, and auditability.
Experience with observability and analytics tools such as Dynatrace, ELK Stack, CloudWatch, or equivalent tools.
Experience working in agile delivery environments where CI/CD, automated testing, code quality, deployment readiness, and production support are critical.
Demonstrated knowledge of software engineering best practices such as version control, software packaging, release management, automated testing, secure coding, and operational readiness.
Strong analytical and problem-solving skills with ability to diagnose complex technical issues independently.
Must be self-motivated, collaborative, and able to communicate effectively with technical and non-technical stakeholders.
What will help you propel from the pack (Preferred Qualifications):
Experience designing and developing enterprise notification, communication, customer messaging, content management, or eventing platform solutions.
Experience with Twilio or similar communication/messaging platforms.
Experience applying AI to communication use cases such as personalization, routing, prioritization, content quality checks, template assistance, intent classification, summarization, or operational anomaly detection.
Experience with AI observability, LLMOps/MLOps practices, model/prompt evaluation, AI guardrails, and production monitoring of AI-enabled features.
AWS certification or equivalent cloud certification.
Experience in high-scale, 24x7 production environments.
Airline, travel, customer platforms, or crew operations domain experience.
Must Have :-
Core AI & Data Engineering -
Tool Calling & Schema Design: Expertise defining functions via JSON schemas to provide agents with toolboxes for executing code, interacting with CRMs, and searching databases.
RAG & Vector Databases: Experience parsing, cleaning, and feeding structured and unstructured data into LLMs, alongside strong knowledge of vector stores (e.g., Pinecone).
Model Context Protocols: Strict adherence to vendor-neutral standards like the Model Context Protocol (MCP) to facilitate standardized, efficient agent-tool integration.
Infrastructure & Deployment -
Containerization & CI/CD: Hands-on experience with Docker, Kubernetes, and CI/CD pipelines to manage scaling, resource orchestration, and production cost monitoring.
Cloud Platforms: Proven familiarity deploying robust, distributed AI architectures on enterprise platforms such as AWS, Google Cloud (Google Cloud Platform), or Azure.
.png%3Fformat%3Dwebp&w=1080&q=75)
Never miss an opportunity! Create an alert based on the job you applied for.