Information Technology_USA - USA_Developer

Real Soft•Jacksonville, FL

4d•Onsite

About The Position

This role involves leading the architecture, design, and implementation of scalable cloud-native backend platforms for Lounge Services. The engineer will design and develop high-performance microservices and APIs using Node.js/TypeScript on AWS/GCP, define architecture standards for distributed systems, event-driven solutions, messaging, and cloud-native applications. A key aspect of the role is driving the adoption of AI capabilities by integrating LLMs and Agentic AI into enterprise backend services, including designing and implementing reusable AI platform components like orchestration, RAG pipelines, model gateways, and AI observability. The position requires providing technical leadership, driving architecture reviews, engineering best practices, and technology decisions. Collaboration with Product, Engineering, Security, and Enterprise Architecture teams is essential for delivering scalable and secure solutions. The role also involves mentoring engineering teams, influencing technical direction, and evaluating emerging backend, cloud, and AI technologies for enterprise adoption, ensuring solutions meet enterprise standards for scalability, reliability, security, performance, and operational excellence.

Requirements

12+ years of experience in designing and building enterprise-scale, cloud-native backend systems and distributed architectures.
Strong hands-on expertise in Node.js, JavaScript, and TypeScript (must-have), with working knowledge of Python and Go.
Extensive experience developing microservices, REST/gRPC APIs, event-driven architectures, and scalable backend platforms.
Strong expertise in AWS and/or GCP, Kubernetes, Docker, cloud-native architecture, and CI/CD pipelines.
Experience with distributed messaging and streaming technologies such as Kafka, queues, and asynchronous processing.
Proven experience designing highly available, secure, scalable, and resilient backend systems.
Strong understanding of databases (SQL/NoSQL), caching, observability, logging, and performance optimization.
Mandatory experience integrating Large Language Models (LLMs) into enterprise applications and backend platforms.
Hands-on experience with Agentic AI frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, or Semantic Kernel.
Experience building Retrieval-Augmented Generation (RAG) pipelines, AI orchestration workflows, and LLM gateways.
Working knowledge of PyTorch, Hugging Face ecosystem, embeddings, inference, and model evaluation.
Strong understanding of AI governance, evaluation, safety, and responsible AI practices.
Excellent architecture, technical leadership, stakeholder management, and mentoring skills.
Languages: Node.js, JavaScript, TypeScript, Python, Go
Cloud: AWS/GCP
Containers: Kubernetes, Docker
APIs: REST, gRPC
Messaging: Kafka or equivalent
AI Frameworks: LangGraph, LangChain, LlamaIndex, CrewAI, Semantic Kernel
ML: Hugging Face, PyTorch
DevOps: CI/CD

Nice To Haves

Terraform (preferred)

Responsibilities

Lead the architecture, design, and implementation of scalable cloud-native backend platforms for Lounge Services.
Design and develop high-performance microservices and APIs using Node.js/TypeScript on AWS/GCP.
Define architecture standards for distributed systems, event-driven solutions, messaging, and cloud-native applications.
Drive the adoption of AI capabilities by integrating LLMs and Agentic AI into enterprise backend services.
Design and implement reusable AI platform components including orchestration, RAG pipelines, model gateways, and AI observability.
Provide technical leadership across engineering teams, driving architecture reviews, engineering best practices, and technology decisions.
Collaborate with Product, Engineering, Security, and Enterprise Architecture teams to deliver scalable and secure solutions.
Mentor engineering teams and influence technical direction across multiple initiatives.
Evaluate emerging backend, cloud, and AI technologies and recommend enterprise adoption where appropriate.
Ensure solutions meet enterprise standards for scalability, reliability, security, performance, and operational excellence.