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

MAS Global Consulting, LLC; 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 deliver production-grade AI applications using Java or Python. You will work across RAG architectures, LLM orchestration, and CI/CD on AWS, shaping end-to-end solutions in a fast-paced in-office environment.

You will contribute to guardrails, evaluation frameworks, and content filtering, while building scalable APIs, microservices, and AI-powered experiences across the stack.

Qualifications

• Bachelor's degree required.
• 10+ years software development experience in Java or Python.
• 7+ years full-stack + Agentic AI development experience.
• 2+ years hands-on production AI/ML applications.
• Strong proficiency with RAG architectures and vector stores.
• Experience with AI orchestration frameworks (LangChain/LlamaIndex/Semantic Kernel/CrewAI).
• Hands-on with AWS Bedrock and Claude models.
• Proven prompt engineering and guardrails practices.

Responsibilities

• Design and build AI/ML applications end-to-end from architecture to production deployment.
• Implement RAG pipelines with chunking, embeddings, and vector store integration.
• Build AI agents using frameworks like LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
• Develop and deploy solutions on AWS Bedrock and Claude model APIs.
• Apply prompt engineering techniques: system prompts, few-shot, structured outputs.
• Create conversational AI experiences: chatbots and voicebots.
• Design and maintain REST/GraphQL APIs, microservices, and event-driven systems.
• Own CI/CD pipelines, containerization (Docker, ECS/EKS), and IaC for production.

Skills

Java or Python

AI/ML development

RAG architectures

LLM orchestration

CI/CD on AWS

APIs & microservices

Prompt engineering

Education

Bachelor's degree

Tools

Pinecone

OpenSearch

pgvector

FAISS

LangChain

LlamaIndex

Semantic Kernel

CrewAI

AWS Bedrock

Anthropic Claude

Job description

Who We Are

MAS Global Consulting is a premium digital engineering partner trusted by innovative startups and Fortune 100 companies to deliver high-impact technology solutions. We combine agile delivery, deep technical expertise, and a people-first culture to build long-term partnerships, not just software.

MAS means "more" in Spanish, and that mindset drives our commitment to creating greater opportunity, inclusion, and impact across the Americas. Founded by a Latina engineer from Medellín and headquartered in Tampa, Florida, MAS Global Consulting is a 100% Hispanic and woman-owned company, recognized as a Great Place to Work and one of the fastest-growing companies in the United States.

The Opportunity

Join a flagship, high-visibility engagement with one of the largest and most influential financial institutions in the United States — an organization where technology decisions are watched at the executive level, and where AI initiatives are expected to set the standard for the rest of the industry.

You'll be part of a large-scale, customer-facing digital transformation: building next-generation, AI-powered booking and travel experiences for millions of end users, with an ambition and level of polish comparable to the world's leading consumer travel platforms. This is not a pilot or a sandbox — it's a strategic, CEO-visible program backed by a delivery organization of 1,000+ engineers and a dedicated AI practice of 50+ specialists, all focused on turning generative AI from experimentation into measurable, production business value.

You will help build production-grade generative AI capabilities that move beyond experimentation and deliver measurable business value, working across RAG, agentic workflows, conversational AI, cloud-native architecture, and responsible AI within a sophisticated enterprise environment.

Who You Are

You are an experienced software engineer who has successfully expanded into AI/ML and generative AI while maintaining strong production engineering fundamentals.

You are comfortable turning complex business needs into scalable technical solutions, from architecture and system design through hands-on development and deployment — including both backend services and the user-facing frontend that consumes them. You understand how to build reliable RAG pipelines, integrate foundation models, connect AI applications to enterprise systems, and deliver software that performs in real production environments, end to end.

You bring sound engineering judgment, curiosity, and a collaborative mindset. You do not need to have worked with every technology listed below, but you should have relevant production experience and the ability to transfer your knowledge across platforms and frameworks.

What You'll Do

• Design, build, test, and deploy production-grade AI/ML and generative AI applications.
• Develop RAG pipelines involving document processing, chunking, embeddings, retrieval, reranking, and vector storage.
• Build agentic workflows that connect foundation models with enterprise data, APIs, tools, and business processes.
• Integrate large language models through managed services and model invocation APIs.
• Develop effective prompting strategies using system instructions, few-shot prompting, tool calling, structured outputs, and context management.
• Build reliable full-stack applications, including backend services and APIs using Java or Python, and the frontend interfaces that expose them to end users.
• Deliver customer-facing product features that directly shape the AI-powered booking and travel experience used by millions of consumers.
• Contribute to scalable microservices, distributed systems, and event-driven architectures.
• Develop conversational AI experiences, including intelligent assistants and chat-based applications.
• Collaborate on cloud deployments, CI/CD pipelines, containerization, infrastructure automation, monitoring, and production support.
• Establish evaluation methods for measuring AI quality, reliability, safety, and business performance.
• Implement guardrails, content controls, observability, and responsible AI practices.
• Partner with product, architecture, engineering, security, and governance teams throughout the delivery lifecycle.
• Contribute to architecture discussions, code reviews, technical decisions, and hands-on problem-solving.

What You Bring

• Bachelor's degree in computer science, engineering, information systems, or a related field.
• Seven or more years of professional software development experience using Java or Python.
• At least two years of hands-on experience building and deploying AI/ML or generative AI applications in production.
• 2+ years of hands-on experience building frontend interfaces (React, Angular, or similar) that integrate with backend services and APIs, with demonstrated ability to own features end to end.
• Strong understanding of RAG architectures, including chunking, embeddings, retrieval strategies, and vector databases.
• Experience integrating large language models through APIs or managed cloud services.
• Experience building AI workflows or agents that use tools, enterprise data, APIs, or multiple processing steps.
• Strong understanding of API design, microservices, distributed systems, and production software engineering.
• Practical experience with cloud services, CI/CD, containerization, and production deployments.
• Ability to evaluate architectural tradeoffs and communicate technical decisions clearly.
• A strong commitment to software quality, security, observability, and responsible AI.

Experience That Will Help You Stand Out

• AWS Bedrock and Anthropic Claude models.
• AWS services such as Lambda, Step Functions, API Gateway, S3, DynamoDB, and SQS.
• LangChain, LlamaIndex, Semantic Kernel, CrewAI, or comparable orchestration frameworks.
• Pinecone, OpenSearch, pgvector, FAISS, or other vector search technologies.
• LLM evaluation frameworks, tracing, observability, and quality measurement.
• Guardrails, content filtering, prompt-injection defenses, and responsible AI controls.
• Docker, ECS, EKS, Kubernetes, and infrastructure as code.
• Experience with React, TypeScript, or modern frontend build tooling.
• REST, GraphQL, and event-driven architectures.
• Speech-to-text, text-to-speech, or voice-enabled AI applications.
• Experience delivering technology within financial services or another highly regulated industry.

Why Join MAS Global

• Work on one of the most strategically visible AI initiatives at a top-tier U.S. financial institution — a program with direct executive sponsorship and outsized influence on the company's broader AI roadmap.
• Solve complex engineering challenges at enterprise scale, on a team of 1,000+ engineers with a growing, well-resourced AI practice.
• Build AI systems designed for real production use, reaching millions of consumers — not proofs of concept.
• Collaborate with experienced professionals across engineering, architecture, product, security, and governance.
• Grow within an inclusive, people-first organization that values technical excellence and diverse perspectives.