MP@Minglong51

About

From the subsurface to systems that act.

I trained as a geophysicist at Rice. At CGG, I built seismic-imaging pipelines: software that turns noisy signal into a picture of something nobody can see directly, and has to say how far that picture can be trusted.

Since 2021 I have been at Amazon, where I work on multi-tenant LLM serving, guardrails, and eval-gated rollouts for real-time translation. Outside work I build small systems of my own and write up what broke.

The habit carried over. I want an AI system to show its state, stay inside its bounds, and interrupt a person only when it is worth their attention.

Trajectory

Four stops, one method.

  1. Rice University · M.S. in Geophysics

    Signal, structure, and uncertainty—the visual language of this atlas begins in seismic imaging.

  2. Viridien (formerly CGG Geophysics) · Software Engineer

    Signal-processing and 3D seismic-imaging pipelines over large subsurface datasets.

  3. Amazon · Software Engineer

    Distributed backend systems, chat infrastructure, and production GenAI translation on AWS.

  4. Independent systems

    Open-source runtimes, personal agent infrastructure, and field notes on keeping AI bounded and observable.

Complete career record

8 yrsdistributed backend and AI infrastructure on AWS
Multi-tenantLLM-serving platform for GenAI translation
Multi-regionreal-time LLM translation serving in production
MCPreusable AI-agent infrastructure adopted across teams
01

Summary

Software engineer building production AI infrastructure for large-scale, customer-facing systems. I own multi-tenant LLM serving, model guardrails, and rollout infrastructure for real-time GenAI translation at Amazon, serving many languages across multiple regions. ~8 years building distributed backend systems across AWS, production operations, and large-scale data processing.

02

Experience

Software Engineer, Amazon

Jun 2021 — Present

Customer Service · GenAI Translation · Chat Infrastructure

AI Platform & Multi-Tenant LLM Serving

  • Designed and own multi-tenant LLM serving for real-time GenAI translation on AWS Bedrock — automated tenant onboarding, request routing, and per-tenant cost tracking across regions, with faster tenant onboarding and improved serving efficiency at production scale.
  • Built the multi-tenant serving and staged-rollout infrastructure used to migrate production traffic from legacy machine translation to GenAI translation on Bedrock — eval-gated dial-up rollouts across many languages and regions.
  • Built a persona-routed MCP server framework (Python FastMCP, stdio) on Anthropic's Model Context Protocol — semantic routing of tasks to persona → skills → tools, with team resource packages and per-team JSON config; adopted by peer teams without forking shared infrastructure.
  • Built MCP-based internal AI agents for developer-productivity and incident-response workflows.
  • Led an enterprise onboarding across European and Japanese marketplaces — large-scale terminology and multilingual configuration, delivered as a staged production change.

Inference Reliability, Safety & Cost Optimization

  • Built guardrails on AWS Bedrock for the GenAI translation stack, screening model output before it reaches customers; extended the translation evaluation framework with standard MT-quality metrics (chrF++, COMET) and LLM-as-judge meaning-preservation checks.
  • Built a direction-aware SageMaker scaling tool with dry-run and rollback that significantly right-sized GenAI inference capacity during the MT→GenAI cutover, materially cutting compute cost.
  • Built staged prompt-rollout controls with a safe kill-switch and per-tenant gating; hardened batch inference with retry/backoff and concurrency limits for reliability under throttling.

Distributed Platform Engineering & Migrations

  • Migrated a regional voice channel to Amazon Connect — resolved cross-region TLS and IAM integration challenges and coordinated multiple partner teams to bring customer-service agents online at scale.
  • Migrated a core chat service to a container-based architecture on ECS/Fargate; built load- and stress-testing infrastructure for active chat monitoring, throttling, and persistence across regions.
  • Led the cross-organization transfer of a suite of chat services between engineering teams — authored knowledge-transfer documentation and ramped the receiving team with no major operational incidents.

Technical Communication

  • Authored internal engineering write-ups on AI developer tooling and MCP-based workflows to socialize reusable AI-infrastructure patterns across teams.

Software Engineer, Viridien (formerly CGG Geophysics)

Jun 2018 — Jun 2021

U.S. Seismic Imaging Department · 3D subsurface imaging workflows for major Oil & Gas clients

  • Built signal-processing and seismic-imaging pipelines in Perl / Java / Python — Fourier transform, Tau-P transform, filter design — on petabyte-scale seismic data spanning 120+ km³ subsurface volume; improved image SNR by 5+ dB.
  • Developed tree-based classification algorithm in Java and released to production; improved workflow throughput, contributing to major proprietary client engagements.
03

Skills

AI / LLM Systems

multi-tenant LLM servingBedrock Guardrailsproduction evalschrF++ / COMET / LLM-as-judgeprompt rolloutMCP / FastMCPAWS BedrockSageMaker

Distributed Systems & Cloud

ECS/FargateLambdaDynamoDBAurora/RDSStep FunctionsCloudWatchCDKevent-driven architecturesmulti-regionobservabilityincident response

Languages

PythonJavaTypeScriptJavaScriptSQLPerlShell
04

Education

Rice University — M.S. in Geophysics

Jul 2016 — May 2018 · Houston, TX

Yangtze University — B.Eng.

Aug 2012 — Jun 2016 · Hubei, China

05

Research & Publications

  • Co-author, Geophysical Research Letters (Carlson et al., 2021) — “Impacts of engineered diversions and natural avulsions on delta-lobe stability.” doi:10.1029/2021GL092438
  • Presentations at American Geophysical Union (AGU) Fall Meeting (2019, 2021) on channel diversion characteristics and delta-lobe stability.