AI/ML Software Engineer

Premier Inn Hotels LLC (UAE); Plano (TX); On-site; USD 90,000 - 96,000; Full time

Job summary

Premier Inn Hotels LLC (UAE) in Plano, TX seeks a Senior Full Stack & Agentic AI Engineer to design, develop, and deploy production-grade AI applications and intelligent agent solutions.

The ideal candidate has 7+ years of software development experience, strong Java and/or Python skills, and hands-on expertise in Generative AI, LLMs, and agentic AI. Interview process includes 2 virtual rounds; final round face‑to‑face in Plano.

Qualifications

• 7+ years of hands-on software development experience.
• Proficiency in Java and/or Python.
• Production experience with Generative AI, LLMs, and Agentic AI.
• Experience with RAG architectures, embeddings, chunking, and vector databases.
• Familiarity with LangChain, Semantic Kernel, CrewAI.
• Experience with AWS Bedrock and Anthropic Claude.
• Strong prompt engineering and LLM application development.
• REST APIs, microservices, and event-driven systems.
• Docker, Kubernetes/EKS/ECS, CI/CD, and Infrastructure as Code.
• Experience building conversational AI and chatbots.

Responsibilities

• Design, develop, and deploy scalable Full Stack and Agentic AI applications.
• Build AI agents, multi-agent workflows, RAG pipelines, and LLM-powered apps.
• Develop backend services and APIs using Java and/or Python.
• Build frontend apps and integrate with AI/ML services.
• Implement RAG solutions with embeddings, chunking, vector DBs, retrieval.
• Work with AWS Bedrock and Anthropic Claude models.
• Use LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
• Develop conversational AI solutions, including chatbots and voice apps.
• Apply prompt engineering with system prompts, few-shot, tool calls, structured outputs.
• Build microservices and event-driven architectures with AWS.
• Implement CI/CD, Docker, Kubernetes, and IaC.
• Develop and integrate REST and GraphQL APIs.
• LLM evaluation, observability, guardrails, content filtering, responsible AI.
• Troubleshoot, optimize, and support production AI apps.

Skills

Java

Python

Generative AI

LLMs

Agentic AI

RAG architectures

LangChain

Semantic Kernel

CrewAI

AWS Bedrock

Anthropic Claude

REST APIs

Microservices

Event-driven systems

Docker

Kubernetes

CI/CD

Infrastructure as Code

Speech-to-text

Text-to-speech

Tools

LlamaIndex

Job description

Location: Plano, TX
Duration: 6 Months Contract
Employment: W2 (USC/GC Only)
Pay Rate: $65-70/hr w2
Interview: 2 rounds virtual; final round face-to-face

Job Overview

We are looking for a SeniorFull Stack & Agentic AI Engineer to design, develop, and deployproduction-grade AI applications and intelligent agent solutions.

The ideal candidate will havestrong software engineering and full-stack development experience, along withhands-on expertise in Generative AI, Agentic AI, RAG, LLMs, andconversational AI.

Candidates with 7+ yearsof software development experience are encouraged to apply, provided theirbackground strongly aligns with Full Stack and Agentic AI development.

Key Responsibilities

• Design, develop, and deploy scalable Full Stackand Agentic AI applications.
  
• Build AI agents, multi-agent workflows, RAGpipelines, and LLM-powered applications.
  
• Develop backend services and APIs using Javaand/or Python.
  
• Build modern frontend applications and integratethem with AI/ML services.
  
• Implement RAG solutions using chunking,embeddings, vector databases, and retrieval techniques.
  
• Work with AWS Bedrock and Anthropic Claude models and APIs.
  
• Use AI frameworks such as LangChain,LlamaIndex, Semantic Kernel, or CrewAI.
  
• Develop conversational AI solutions, includingtext chatbots and voice-enabled applications.
  
• Apply prompt engineering techniques includingsystem prompts, few-shot prompting, tool calling, and structured outputs.
  
• Build scalable microservices and event-drivenarchitectures using AWS services.
  
• Implement CI/CD, Docker, Kubernetes/EKS/ECS, andInfrastructure as Code.
  
• Develop and integrate REST and GraphQL APIs.
  
• Implement LLM evaluation, observability,guardrails, content filtering, and responsible AI practices.
  
• Troubleshoot, optimize, and support production AIapplications.
  

Required Qualifications

• 7+ years of hands-on software developmentexperience.
  
• Strong proficiency in Java and/or Python.
  
• Hands-on production experience with GenerativeAI, LLMs, and Agentic AI.
  
• Strong experience with RAG architectures,embeddings, chunking, and vector databases.
  
• Experience with one or more of:
  
• LangChain
  
• Semantic Kernel
  
• CrewAI
  
• Hands-on experience with AWS Bedrock andAnthropic Claude.
  
• Strong understanding of prompt engineering andLLM application development.
  
• Experience with REST APIs, microservices, andevent-driven systems.
  
• Experience with AWS services including:
  
• Lambda
  
• Step Functions
  
• API Gateway
  
• S3
  
• DynamoDB
  
• SQS
  
• Experience with Docker, Kubernetes/EKS/ECS,CI/CD, and Infrastructure as Code.
  
• Experience building conversational AI, chatbots,or voice-enabled AI applications.
  

Requirements

Preferred Qualifications

• Experience with Pinecone, OpenSearch,pgvector, or FAISS.
  
• Experience with LLM evaluation and observabilityframeworks.
  
• Experience implementing AI guardrails, contentfiltering, and responsible AI practices.
  
• Experience integrating speech-to-text andtext-to-speech technologies.
  
• Financial services or banking industryexperience.
  
• Experience working in enterprise-scale and highlyregulated environments.