Open to opportunities

Dexter Anderson

@dexteranderson

Message

I’m a Senior Full Stack AI Engineer building production-grade GenAI, LLM, RAG, and agentic systems.

United States

Message

What I'm looking for

I’m looking to build and ship production-grade GenAI and agentic systems end-to-end, partnering with product and data teams to deliver measurable outcomes through robust RAG, evaluation, and LLM observability.

I’m a Senior Full Stack AI Engineer with 10+ years of experience architecting and delivering production-grade software, with 6+ years of deep specialization in Generative AI, Large Language Models, RAG architectures, and Agentic AI workflows.

I embed LLM-powered capabilities into enterprise products across healthcare, real estate, and financial domains, combining full-stack engineering depth with hands-on delivery of LangChain/LangGraph and cloud-deployed agentic systems end-to-end—from prompt design and vector retrieval to scalable deployment and LLM observability.

I’m known for owning systems from architecture to production while aligning engineering decisions with measurable product and business outcomes, including ~60% faster query responses, ~42% inference cost reductions, and significant Azure OpenAI cost and latency improvements through caching, evaluation, and governance tooling.

Experience

Work history, roles, and key accomplishments

Senior AI/ML Platform Engineer

Accenture

Feb 2025 - Mar 2026 (1 year 1 month)

Architected and delivered an Agentic RAG platform on AWS ECS using AWS Bedrock, LangGraph, and Qdrant—reducing knowledge query response time by ~60% for 200+ daily users. Built LLM observability and cost governance with LangSmith, Arize Phoenix, and CloudWatch, cutting inference costs by ~42% while standardizing Docker/Kubernetes deployments and Terraform-based CI/CD.

Agentic RAG LangGraph Qdrant AWS ECS Langsmith Terraform Kubernetes

AI/ML Engineer

Informulate

May 2022 - Nov 2024 (2 years 6 months)

Built an enterprise RAG chatbot on Azure using LangChain, Azure OpenAI, and Azure AI Search, enabling 50+ engineers to query 3 years of project history and policy documents in natural language. Integrated Redis semantic caching to cut Azure OpenAI API costs by ~30% and reduced average response latency from ~4 seconds to ~1 second, and deployed ingestion and extraction pipelines via AKS (Helm CI/CD

Azure OpenAI Azure AI Search Lang Chain LangGraph Redis AKS Helm Azure Functions PyMuPDF

Software Engineer (Backend & Full Stack)

End Point Dev

Apr 2019 - Mar 2022 (2 years 11 months)

Built and scaled cloud-native backend services and REST APIs on AKS/EKS, implementing Prometheus/Grafana monitoring and ELK logging while reducing infrastructure costs by ~25–35% via right-sizing, spot instances, and autoscaling. Delivered full-stack enterprise applications using .NET Core (C#, MVC, Web API) and Angular/React hosted on AWS (EC2, RDS, Lambda, S3), with Terraform/Python/Lambda autom

Prometheus Grafana ELK Stack C# .NET Core REST APIs Angular React AWS Lambda Terraform Docker

Software Engineer (Data & Integration)

Infitech IT Solution Pvt. Ltd

Sep 2016 - Feb 2018 (1 year 5 months)

Built and maintained .NET and Python enterprise applications and supported early Azure cloud migration with RESTful API development. Developed integration-centric web applications and structured data workflows/API integrations to improve interoperability across client systems with secure, testable, maintainable code.