Senior AI/ML Full-Stack Engineer: RAG & LLM Orchestration

MAS Global Consulting; Plano (TX); On-site; USD 140,000 - 190,000; Full time

Job summary

MAS Global Consulting is seeking a Senior AI/ML Full Stack Engineer to design and deploy production-grade AI applications. You will build end-to-end systems, including RAG pipelines, vector stores, and AI agents, using Java or Python in a fast-paced, in-office environment in the US.

You will work with LangChain, LlamaIndex, Semantic Kernel, and CrewAI, deploying on AWS Bedrock and Claude models, with strong emphasis on guardrails and responsible AI practices.

Qualifications

• Bachelor's degree required.
• 10+ years of software development experience (Java or Python), OR 7+ years if entirely full-stack + Agentic AI development experience.
• 2+ years hands-on experience building AI/ML applications in production.
• Strong proficiency with RAG architectures — chunking strategies, embedding models, vector stores.
• Experience with AI orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
• Hands-on experience with AWS Bedrock, Anthropic Claude models, and model invocation APIs.
• Proven prompt engineering skills — system prompts, few-shot, chain-of-thought, tool use, structured outputs.
• Experience building conversational AI: chatbots (text) and voicebots.
• Proficiency with AWS services (Lambda, Step Functions, API Gateway, S3, DynamoDB, SQS).
• Experience with CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructure-as-code.
• Strong understanding of API design (REST, GraphQL), microservices architecture, and event-driven systems.
• Familiarity with evaluation frameworks for LLM outputs.
• Experience with guardrails, content filtering, and responsible AI practices

Responsibilities

• Design and build AI/ML applications end-to-end, from architecture through production deployment.
• Implement RAG pipelines, including chunking strategies, embedding models, and vector store integration.
• Build and orchestrate AI agents using frameworks such as LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
• Develop and deploy solutions using AWS Bedrock, Anthropic Claude models, and model invocation APIs.
• Apply advanced prompt engineering techniques — system prompts, few-shot, chain-of-thought, tool use, structured outputs.
• Build conversational AI experiences, including chatbots (text) and voicebots (speech-to-text, text-to-speech).
• Design and maintain APIs (REST, GraphQL), microservices, and event-driven architectures.
• Own CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructure-as-code for production systems.
• Implement evaluation frameworks, guardrails, content filtering, and responsible AI practices across LLM-powered features.

Skills

AI/ML full stack development

Prompt engineering

Agentic AI development

Production-grade software development

Hands-on problem solving

Education

Bachelor's degree

Tools

Pinecone

OpenSearch

pgvector

FAISS

LangChain

LlamaIndex

Semantic Kernel

CrewAI

AWS Bedrock

Anthropic Claude

Docker

ECS/EKS

API Gateway

Lambda

S3

DynamoDB

SQS

Job description

MAS Global Consulting is seeking a Senior AI/ML Full Stack Engineer to design and deploy production-grade AI applications. You will build end-to-end systems, including RAG pipelines, vector stores, and AI agents, using Java or Python in a fast-paced, in-office environment in the US.

You will work with LangChain, LlamaIndex, Semantic Kernel, and CrewAI, deploying on AWS Bedrock and Claude models, with strong emphasis on guardrails and responsible AI practices.