Java Full stack Engineer

ClifyX; Irving (TX); Hybrid; USD 130,000 - 160,000; Full time

Job summary

A leading AI technology firm seeks a Full-Stack AI Engineer to drive innovation in AI-powered products. This pivotal role involves designing and deploying end-to-end applications, optimizing pipelines, and collaborating in a dynamic environment. Ideal candidates will bring over 5 years of software engineering experience, with substantial knowledge in AI frameworks and microservices. The position offers a hybrid work model based in Irving, TX, requiring a strong background in modern web technologies and AI system architecture.

Qualifications

• 5+ years of progressive professional software engineering experience.
• 1-2 years of experience building and deploying AI-powered solutions.
• Extensive experience with Large Language Models (LLMs).
• Proficiency in designing and implementing RAG architectures.

Responsibilities

• Design, develop, and deploy Full-Stack AI applications.
• Architect and implement agentic AI systems for multi-step reasoning.
• Optimize RAG pipeline design for retrieval performance.
• Build scalable back-end services integrating LLMs and APIs.

Skills

Core Java

React

Spring

AI/GenAI Research

Education

B.Tech/B.Eng. degree or equivalent work experience

Tools

Docker

Kubernetes

AWS

Terraform

Job description

Location: Irving, Tx / Tampa, FL (Hybrid 3 days onsite)

Location: Irving, Tx / Tampa, FL (Hybrid 3 days onsite)

Required skill: Core Java, React, Spring boot

Join our pioneering team as a Full-Stack AI Engineer and be at the forefront of building the next generation of intelligent AI-powered products that redefine user experiences and solve complex business challenges. This pivotal role empowers you to own the entire solution stack—from intuitive front-end interfaces to robust back-end infrastructure and cutting-edge agentic AI systems. You will play a critical role in designing, developing, and deploying high-impact AI-driven solutions, driving engineering excellence, and influencing our software architecture. We’re seeking a passionate problem-solver who thrives in a collaborative, agile environment, dedicated to crafting innovative solutions and contributing to a vibrant technical community.

Key Responsibilities

• Pioneer Full-Stack AI Application Development: Design, develop, and deploy transformative end-to-end applications leveraging modern web frameworks (React, Next.js), FastAPI (Python), and Java, with Large Language Models (LLMs) at their core.
• Architect Agentic AI Systems: Lead the design and implementation of sophisticated autonomous agents capable of multi-step reasoning, planning, and dynamic task execution using frameworks like LangChain, LangGraph, or AutoGen.
• Innovate RAG Pipeline Design: Architect and optimize production-grade Retrieval-Augmented Generation (RAG) pipelines, focusing on advanced embedding strategies, efficient vector database management (Pinecone, Milvus, Chroma), and superior retrieval performance.
• Build Scalable Back-End & API Integrations: Develop highly performant asynchronous back-end services that seamlessly integrate LLMs, external APIs, and tools, ensuring exceptional reliability and ultra-low latency.
• Optimize Data & Database Management: Strategically manage structured and unstructured data, overseeing both traditional SQL/NoSQL databases and advanced vector databases to enable context-aware and intelligent AI systems.
• Champion Engineering Excellence & Agile Delivery: Drive best practices in code quality, unit testing, CI/CD, and security. Act as a strong contributor within an agile software delivery team, collaborating to achieve sprint goals and actively participating in the broader Citi technical community and Agile/Scrum processes.

Required Qualifications

• 5+ years of progressive professional software engineering experience, with a minimum of 1-2 years dedicated to building and deploying AI-powered solutions.
• Extensive hands‑on experience with Large Language Models (LLMs) (e.g., OpenAI GPT, Anthropic Claude, Gemini, Llama), including fine‑tuning techniques and advanced prompt engineering.
• Proven expertise in designing and implementing RAG architectures, encompassing embedding strategies, vector stores, and semantic search.
• Deep experience with microservices; designing and implementing RESTful/GraphQL APIs; and practical application of containerization technologies (Docker/Kubernetes/OpenShift).
• Practical experience with agentic frameworks (LangChain, LangGraph, AutoGen, CrewAI, etc.), including designing, implementing, and orchestrating multi‑agent systems.
• Solid understanding and practical application of frameworks such as Spring Boot, FastAPI, Express, etc.
• Significant experience working within agile and iterative software delivery methodologies (SAFe, Scrum, Kanban).
• Proficiency in various database technologies, including advanced SQL and vector databases (Oracle, PostgreSQL, MongoDB, Aurora, Pinecone, pgvector, etc.).
• Experience with event‑driven design and architecture (e.g., SQS, SNS, Kinesis, Kafka, Spark, Flink, RabbitMQ).
• B.Tech/B.Eng. degree or equivalent work experience.

Preferred Qualifications

• Experience in designing and implementing complex multi‑agent collaboration architectures.
• Familiarity with AI‑driven development tools (e.g., Cursor, Claude, Copilot) to enhance productivity.
• Proven architectural experience in building horizontally scalable, highly available, highly resilient, and low‑latency applications.
• Experience with both on‑premises and public cloud infrastructure (e.g., OpenShift, AWS), including Infrastructure as Code tools (e.g., Terraform, CloudFormation).
• Knowledge of security, observability, and monitoring tools (e.g., Grafana, Prometheus, Splunk, ELK, CloudWatch).
• Prior experience mentoring and providing technical leadership to teams of 5 or more developers.
• Familiarity with job schedulers (e.g., Apache Airflow, AutoSys, CloudWatch).

Skills

Mandatory Skills : AI/GenAI Research, Java, React, Spring