Engineer - Generative AI

As a Generative AI Engineer at United's Digital Technology team, your role will involve designing and scaling AI-native platforms and services. You will utilize your full-stack engineering foundation and hands-on experience in Generative AI, cloud-native architectures, and MLOps to contribute to the development of intelligent systems, AI agents, and reusable platforms across backend, frontend, and middleware layers. Your responsibilities will include: - Designing, developing, and deploying AI-native applications and services leveraging Generative AI and LLMs - Building and maintaining end-to-end solutions across backend (Python), middleware, and frontend layers - Developing scalable APIs and microservices to enable AI-driven capabilities across platforms - Implementing and operationalizing LLM-based workflows, including prompt orchestration, RAG pipelines, and agent frameworks - Contributing to architecture design and system decomposition to ensure scalability, resilience, and extensibility - Building and managing cloud-native solutions on AWS, leveraging services such as Lambda, ECS/EKS, S3, and API Gateway - Establishing and maintaining MLOps practices, including CI/CD pipelines, model deployment, versioning, and monitoring - Implementing observability and telemetry frameworks (logging, tracing, metrics) to ensure reliability and performance of AI systems - Collaborating with cross-functional teams to translate business requirements into scalable technical solutions - Continuously optimizing performance, cost, and latency of AI workloads and services To succeed in this role, you will need: - 35 years of experience in software engineering with strong hands-on development skills and exposure to system design - Proficiency in Python for backend development - Experience with frontend frameworks (e.g., React, Angular, or equivalent) - Strong understanding of API design, middleware, and microservices architecture - Hands-on experience with Generative AI technologies (LLMs, prompt engineering, RAG, vector databases) - Experience working with AWS cloud infrastructure and building cloud-native applications - Familiarity with MLOps practices and tools for model lifecycle management - Working knowledge of observability and telemetry (e.g., OpenTelemetry, Prometheus, Grafana, CloudWatch) - Understanding of data storage and retrieval systems (relational, NoSQL, and vector databases) Preferred qualifications that will set you apart include: - Experience building AI agents or autonomous systems - Exposure to platform engineering concepts such as control plane and application plane architectures - Familiarity with lightweight SDKs and developer enablement tools - Knowledge of AI evaluation, governance, and responsible AI practices - Experience optimizing LLM performance, scalability, and cost efficiency Key competencies for success in this role include: - Strong problem-solving and analytical thinking - Ability to operate across multiple layers of the technology stack - Balance of execution excellence and architectural thinking - Effective collaboration and communication skills - Continuous learning mindset in a rapidly evolving AI ecosystem As a Generative AI Engineer at United's Digital Technology team, your role will involve designing and scaling AI-native platforms and services. You will utilize your full-stack engineering foundation and hands-on experience in Generative AI, cloud-native architectures, and MLOps to contribute to the development of intelligent systems, AI agents, and reusable platforms across backend, frontend, and middleware layers. Your responsibilities will include: - Designing, developing, and deploying AI-native applications and services leveraging Generative AI and LLMs - Building and maintaining end-to-end solutions across backend (Python), middleware, and frontend layers - Developing scalable APIs and microservices to enable AI-driven capabilities across platforms - Implementing and operationalizing LLM-based workflows, including prompt orchestration, RAG pipelines, and agent frameworks - Contributing to architecture design and system decomposition to ensure scalability, resilience, and extensibility - Building and managing cloud-native solutions on AWS, leveraging services such as Lambda, ECS/EKS, S3, and API Gateway - Establishing and maintaining MLOps practices, including CI/CD pipelines, model deployment, versioning, and monitoring - Implementing observability and telemetry frameworks (logging, tracing, metrics) to ensure reliability and performance of AI systems - Collaborating with cross-functional teams to translate business requirements into scalable technical solutions - Continuously optimizing performance, cost, and latency of AI workloads and services To succeed in this role, you will need: - 35 years of experience in software engineering with strong hands-on development skills and exposure to system design - Proficiency in Python for backend development - Experience wit