• What Happens Between the Prompt and the Response

  Most people interact with LLMs through an API and never think about what sits between the model weights and the HTTP response. A look at the two-phase execution model, the KV cache, and why llama.cpp and vLLM solve fundamentally different problems.
• Building with Intention: Spec-Driven Development with GitHub Spec-Kit

  How writing the spec first — and letting it govern the entire development cycle — maps naturally to Scrum roles, keeps AI-assisted code generation honest, and delivers real velocity to the SDLC.

• Jan2022 - Current
  Concord
  Senior Software Engineer

  Senior Software Engineer | St. Louis Park, MN | May 2025 – Present

  Software Engineer | St. Louis Park, MN | Jan 2024 – April 2025

  Client: Agricultural Services

  • Engineered schema-driven Spring Boot microservices that power end-to-end B2B EDI transaction tracking across multiple business domains within a Hub-Spoke integration architecture
  • Improved error visibility by building React/TypeScript tools with GraphQL endpoints surfacing complex entity relationships, exposing raw documents and Pulsar-driven real-time status, with standardized JSON logs and Datadog dashboards for real-time transaction monitoring
  • Delivered scalable, containerized microservices on Amazon EKS with a dual-database pattern (PostgreSQL writes + MongoDB historical reads) and Redis for token caching and distributed transaction locking to boost throughput and reliability for high-volume EDI traffic
  • Collaborated closely with SAP, Boomi and data teams to align payload schemas, resolve contract mismatches, and ensure reliable bi-directional data flow between ERP systems and external trading partners

  ---

  Associate Software Engineer | St. Louis Park, MN | Jan 2022 – Dec 2023

  Client: Logistics Services

  • Developed REST based Java applications following service oriented architecture set up in containers and deployed across a Kubernetes cluster
  • Worked closely with clients to identify performance bottlenecks with managing web service calls to downstream applications
  • Leveraged performance testing tools like Locust to simulate high traffic and gather insightful telemetry into application data usage
  • Partnered with cross-functional teams in Agile ceremonies, driving backlog refinement and ensuring timely delivery of Sprint goals
• Jun2021 - Jan2022
  Northteq
  Software Developer
  • Supported client business needs by designing workflows and triggers built on Apex with technical design documentation
  • Deployed changes to business-facing applications hosted on AppExchange plus API integrations and managed package maintenance

• LLM Inference Explorer

  A local Python app that serves a quantized LLM via Ollama and exposes it through a Streamlit UI — built to make inference engine concepts tangible through live metrics and reproducible benchmarks.
• EdiTrack API

  A production-grade EDI X12 transaction ingest platform built on ASP.NET Core — tackling an enterprise-scale integration problem at a local demo footprint.

Let's Connect

• github /
• linkedin /
• mehtazmuntaqim@gmail.com