Full Stack AI Engineer

Location: Plano, TX — Onsite, 5 days/week (Who We AreAt MAS Global Consulting, we are a premium digital engineering partner trusted by innovative startups and Fortune 100 companies, delivering high-impact solutions through agile delivery, deep technical expertise, and a strong people-first culture across the Americas.We build long-term partnerships, not just software. MAS means "more" in Spanish, and that mindset drives our commitment to greater opportunity, inclusion, and impact.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 US.Who You AreYou are a Senior AI/ML Full Stack Engineer who brings deep hands-on experience building production-grade AI applications with Java or Python. You've spent 7-10+ years mastering full-stack development and have moved confidently into agentic AI, RAG architectures, and LLM orchestration. You're just as comfortable designing a vector store retrieval pipeline as you are hardening a CI/CD deployment on AWS. You thrive in fast-paced, in-office environments where live coding and hands-on problem solving are part of the culture, and you're excited to bring responsible AI practices — guardrails, evaluation frameworks, and content filtering — into everything you build.What You'll DoDesign and build AI/ML applications end-to-end, from architecture through production deploymentImplement RAG pipelines, including chunking strategies, embedding models, and vector store integration (Pinecone, OpenSearch, pgvector, FAISS)Build and orchestrate AI agents using frameworks such as LangChain, LlamaIndex, Semantic Kernel, or CrewAIDevelop and deploy solutions using AWS Bedrock, Anthropic Claude models, and model invocation APIsApply advanced prompt engineering techniques — system prompts, few-shot, chain-of-thought, tool use, structured outputsBuild conversational AI experiences, including chatbots (text) and voicebots (speech-to-text, text-to-speech)Design and maintain APIs (REST, GraphQL), microservices, and event-driven architecturesOwn CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructure-as-code for production systemsImplement evaluation frameworks, guardrails, content filtering, and responsible AI practices across LLM-powered featuresWhat You BringBachelor's degree required10+ years of software development experience (Java or Python), OR 7+ years if entirely full-stack + Agentic AI development experience2+ years hands-on experience building AI/ML applications in productionStrong proficiency with RAG architectures — chunking strategies, embedding models, vector stores (Pinecone, OpenSearch, pgvector, FAISS)Experience with AI orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or CrewAIHands-on experience with AWS Bedrock, Anthropic Claude models, and model invocation APIsProven prompt engineering skills — system prompts, few-shot, chain-of-thought, tool use, structured outputsExperience building conversational AI: chatbots (text) and voicebots (speech-to-text, text-to-speech)Proficiency with AWS services (Lambda, Step Functions, API Gateway, S3, DynamoDB, SQS)Experience with CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructure-as-codeStrong understanding of API design (REST, GraphQL), microservices architecture, and event-driven systemsFamiliarity with evaluation frameworks for LLM outputsExperience with guardrails, content filtering, and responsible AI practices