Skip to main content
John GoinsJG
Looking for a job

John Goins

@johngoins

Staff AI Engineer at Northstar Ingredient Intelligence who raised grounded-answer acceptance from 68% to 86% for compliance questions.

United States
Message

At Northstar Ingredient Intelligence, I defined a reference architecture for retrieval-augmented agents combining Azure OpenAI, Azure AI Search, PostgreSQL, enterprise APIs, and human approval checkpoints. I reworked supplier-document retrieval, raising grounded-answer acceptance from 68% to 86% across a controlled evaluation set of compliance questions.

I built reusable Python services and deployment templates for connecting agents to enterprise APIs, with shared security and observability. By combining extraction, evidence-linked summaries, deterministic policy checks, and human sign-off, I reduced analyst review time for ingredient-change workflows from 42 minutes to 17 minutes.

Before Northstar, I designed a multi-tenant document intelligence platform at Harborline Commerce Systems and built data services at Cobalt Data Works, Meridian Integration Group, and Pioneer Digital Services. Across these roles, I improved workflow reliability and performance, developed production integrations, and introduced testing and evaluation practices; I also hold Microsoft Azure AI and Solutions Architect certifications and an AWS Machine Learning certification.

Experience

Work history, roles, and key accomplishments

NI
Current

Staff AI Engineer

Northstar Ingredient Intelligence

Jun 2022 - Present (4 years 5 months)

Defined a reference architecture for retrieval-augmented agents and improved grounded-answer acceptance from 68% to 86%. Reduced median workflow latency from 9.4 to 5.8 seconds and analyst review time from 42 to 17 minutes.

HS

Principal Machine Learning Engineer

Harborline Commerce Systems

Jan 2020 - May 2022 (2 years 4 months)

Designed a multi-tenant document intelligence platform and improved document classification macro-F1 from 0.71 to 0.84. Reduced batch enrichment cost from 18.6 to 11.2 cents per document and raised successful automated workflow completion from 79% to 91%.

MG

Software Engineer

Meridian Integration Group

Aug 2015 - Jun 2017 (1 year 10 months)

Implemented C# and Python services integrating supplier portals, ERP systems, and document repositories. Cut partner-feed processing time from 4.2 to 1.6 hours and added automated testing and deployment pipelines.

C#PythonRESTSOAPSQL
Database Schemas
Data ValidationUnit TestingIntegration Testing
Build Pipelines
Deployment Scripts
Logging

Education

Degrees, certifications, and relevant coursework

Princeton University logoPU

Princeton University

Master of Science, Computer Science

Master of Science in Computer Science from Princeton University, completed in May 2017.

MI

Microsoft

Microsoft Certified: Azure AI Engineer Associate, Azure AI

Microsoft Certified: Azure AI Engineer Associate certification.

MI

Microsoft

Microsoft Certified: Azure Solutions Architect Expert, Azure Solutions Architecture

Microsoft Certified: Azure Solutions Architect Expert certification.

AS

Amazon Web Services

AWS Certified Machine Learning – Specialty, Machine Learning

AWS Certified Machine Learning – Specialty certification.

Availability

Looking for a job

Location

United States

Authorized to work in

Salary expectations

60k+ USD

Interested in hiring John?

You can contact John and 600K+ other talented remote workers on Himalayas.

Message John

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan