BM
Blake Martin
Blake Martin

Blake Martin

AI Engineer

Building production AI systems that scale. Specializing in intelligent automation, multi-agent architectures, and MLOps pipelines that drive real business impact.

Technical Skills

General

PythonTypeScriptJavaScriptSQLJavaHTML/CSS

Machine Learning

PyTorchTensorFlowScikit-learnXGBoost

MLOps & Production

DockerAWS SagemakerMLflowFastAPI

Data & Vector

FAISSWeaviatePostgreSQLApache Airflow

AI Frameworks

LangGraphLangChainTransformersLlamaIndex

Notable Projects

Production Planning & Operations Platform

Client: Regional nonwovens fabric manufacturer • $5M+ revenue • 40+ employees

Web platform replacing spreadsheet workflows with centralized order management, job optimization, and real-time production tracking across day and night shifts.

Core Features

Order Management

  • Order sequencing interface for job grouping and reordering to minimize knife changes and setup time
  • Job-combination optimization algorithm reducing excess roll production by 70% per order, cutting inventory buildup and waste
  • Automated production worksheet generation from optimized sequences for floor operators

Shift Reporting:

  • Digital shift reports for supervisors to track output, downtime, waste, and quality metrics across crews
  • Automatic rollup of shift data into daily, weekly, monthly, and yearly summaries
  • 50 hours/month saved in administrative overhead through workflow automation

Deployment:

  • Full deployment, onboarding, and training for planners and supervisors
  • Functional testing, reconciliation checks, and UAT for operational and audit compliance
  • Validation documentation covering system behavior, assumptions, and maintenance procedures
FastAPISQLPythonTypeScript

"Blake has been an excellent partner and very easy to work with. He automated a significant portion of our planning workload, enabling meaningful efficiency gains on the production line."

— T. Robbins, CEO

Enterprise Sales Analytics Dashboard

Client: National windows manufacturer • $30M+ revenue • 50+ employees

Multi-page internal analytics dashboard for leadership, sales management, and account teams to monitor performance, client activity, quotes, discounts, and product trends. Consolidates invoice, quote, and product-level data with filtering by client, rep, product line, geography, and time period.

Core Features

Analytics & Reporting:

  • YTD and prior-year tracking at client, rep, store, state, and regional levels with drill-downs from executive summaries to individual months and transactions
  • Growth and decline identification for top clients and YoY sales performance analysis by rep to measure performance trends
  • Product-level trend analysis with side-by-side comparisons and rolling metrics to identify demand shifts, product mix changes, and seasonality
  • Automated discount reporting by rep, client, and category for margin impact evaluation and commission calculations
  • Quote volume, conversion rates, days-to-close, and open order value tracking with auditability through invoice-level drill-downs

Deployment:

  • End-to-end deployment including Microsoft tenant setup, workspace configuration, access control, and sales team onboarding
  • Comprehensive client documentation covering dashboard structure, data definitions, and modification guidance for non-technical users
Power BISQLSQL ServerAzure

Academic Advising & Degree Audit Platform

Client: Regional university • 1000+ students

Advising platform automating degree audits, course history review, and course recommendations. Centralizes student records and program requirements for tracking degree progress and supporting advising decisions.

Core Features

Degree Tracking:

  • Automated degree audits breaking down requirements by category with completed vs. remaining credit indicators
  • Progress tracking showing completion percentage, credit totals, and upper-level credit requirements
  • Term-by-term academic history with course records and grades for advising conversations

Course Recommendations:

  • Recommendation engine surfacing remaining requirements and eligible courses based on program rules and student progress
  • Real-time course availability data including instructors, delivery format, and seat counts for schedule planning
  • Direct schedule-building from recommendations to streamline advising sessions

Implementation:

  • Full-stack development: backend API design, data access layer, and frontend interface
  • Secure data access to student records and program requirements with validation and error handling
  • Deployment and environment configuration for advisor and student access
FastAPIPostgreSQLReactREST API

Side Projects

Mailix: AI Email Automation Platform

Production email automation platform using LangGraph multi-agent workflows for intelligent email classification, prioritization, and response generation. Implemented vector-based memory retrieval with Pinecone and cost-optimized inference by hosting DeepSeek on RunPod, achieving 94.2% classification accuracy and processing 150 emails/minute with <2.5s response times.

Technical Highlights:

  • Multi-agent workflow orchestration with LangGraph
  • Vector memory system for contextual responses
  • Cost-optimized inference with DeepSeek on RunPod
  • Real-time email processing at scale
LangGraphLlamaIndexPineconeFastAPINext.jsOpenAIDeepSeekRunPod

Advanced Gmail ML Pipeline

Personal project building sophisticated email intelligence system combining RoBERTa sentiment analysis, UMAP+HDBSCAN clustering, and predictive analytics. Features multimodal processing with BLIP/CLIP vision models, semantic search with FAISS/Weaviate, and agent-based architecture processing 5M+ emails.

Technical Highlights:

  • Multimodal content processing with vision transformers
  • Advanced clustering with UMAP dimensionality reduction
  • Real-time sentiment analysis and predictive timing
RoBERTaUMAPHDBSCANFAISSWeaviatePyTorchFastAPI

What Colleagues Say

"Blake consistently broke down complex problems into manageable parts and delivered thoughtful, efficient solutions. His accountability, attention to detail, and drive to improve made a real impact on both our operations and team culture."

Kevin Yen

CEO & Co-Founder, FlowData.ai

"Blake led cross-functional teams, built engaging educational products, and consistently pushed to improve our programs and processes. He's sharp, driven, and brings a contagious energy to the team."

Alex Duffy

Head of AI, Every Inc.

Machine Learning Newsletter

Weekly insights on emerging AI technologies. Join 2,600+ ML engineers following my technical deep-dives.

Beyond the Code: MCP — The End of AI Integration Hell

Technical deep-dive into Model Context Protocol and how it's solving the fundamental challenge of connecting LLMs to production systems. Covers architecture patterns, implementation details, and real-world tradeoffs.

Featured: MCP Architecture, JSON-RPC Implementation, Production Patterns

Google's Prompt Engineering Bible & Hugging Face's Agents

Analysis of Google's prompt engineering best practices and Hugging Face's new agent frameworks. Practical insights for building reliable LLM applications.

Featured: Prompt Engineering, Agent Frameworks, Production LLMs

OpenAI's Million-Token GPT-4.1 & Google's A2A Protocol

Technical breakdown of OpenAI's extended context windows and Google's Agent-to-Agent communication protocol. Implications for large-scale AI system architecture.

Featured: Extended Context, A2A Protocol, System Architecture

Let's Build Something Great

I'm always excited to discuss ML engineering challenges, system architecture decisions, or opportunities to build scalable AI systems that drive real business value.

Get In Touch