# Nathan Marley

> Lead/Staff Software Engineer | Rust, Python | Building RAG and Agentic Systems with LLMs | AI-First Product Builder

Location: United States, United States
Profile: https://flows.cv/nathanmarley

Staff-level software engineer with 17+ years building scalable systems, distributed backends, and AI-integrated products.

I've created products like Speakeasy (Whisper-based macOS voice app) and ShipMind (agentic context engine with RAG).

Focused on fast delivery, clean architecture, and building systems that extend human capability.

Fluent in Rust, Go, Python, and TypeScript.

Currently focused on applied AI systems, agentic frameworks, and LLM integration for real-world tools.

Open to impactful roles or high-leverage consulting work.

## Work Experience
### Lead Software Engineer @ Glowberry Labs
Jan 2024 – Present
- Built and launched Speakeasy, a macOS app in Swift/AppKit that transcribes your voice seamlessly into any text field using Whisper (OpenAI); users average 15 transcription hours per month
- Created ShipMind, a context-aware personal agent system with Postgres + pgvector for RAG-based memory, Bun + Fastify backend for routing and session management, and a Python-based microservice that standardizes multi-provider LLM execution; currently architecting the core agent framework
- Developed Python and Rust based LLM API gateway microservices integrating OpenAI, Anthropic, xAI, and Google, standardizing model access, prompt/response formats, vector embeddings and token usage across 25+ models

### Team Lead/Senior Software Engineer @ SupplyPike
Jan 2023 – Jan 2024 | Rogers, Arkansas, United States
- Led the normalization and optimization of Postgres DB schema, reducing storage by 66% and processing time by 80%+ in most queries
- Introduced Rust for concurrent processing of 12TB of data (~12m files)
- Optimized CI/CD pipeline by migrating from ESLint/Prettier to Biome, reducing build times by 90-180 seconds per PR
- Built and integrated multiple shipping document scrapers in NestJS (Node.js/TypeScript) within a distributed system processing 30-40k nightly tasks

### Independent Software Developer @ Private Freelance Clients
Jan 2021 – Jan 2023 | remote
- Enabled searchable tracking of naturalization records by extracting and indexing 6,600+ official gazette PDFs using a Rust-based ETL pipeline with fuzzy regex matching and Tantivy full-text search
- Increased system reliability under unstable data sources by implementing exponential backoff, retry logic, and fault-tolerant scraping architecture
- Designed PostgreSQL/Diesel ORM schema and deployed on AWS infrastructure with Terraform, Docker, and automated scheduling
- Achieved 20–30% storage savings on test datasets by prototyping a Rust-based encrypted archival system with chunk-level de-duplication and asymmetric encryption via age; added Amazon S3 support and a CLI for metadata tagging, search, and selective restore
- Built real-time weather monitoring firmware in Rust for RP2040 and STM32 microcontrollers interfacing with BME680 sensor via I2C, optimizing memory usage to <32KB RAM

### Lead Software Engineer @ Dash - Digital Cash (Cryptocurrency)
Jan 2017 – Jan 2023
- Rebuilt the Decentralized Governance By Blockchain (DGBB) system in Python, improving reliability and fixing payout errors for ~4200 Dash masternodes
- Established code quality standards, increasing test coverage by 40% for Node.js and Go codebases
- Developed Go bindings for Chia Network's BLS Signatures C++ library using CGo for cross-language cryptographic support
- Engineered blockchain sync system reducing full-node sync from 3+ days to 5 minutes, enabling rapid deployment of devnets with 100+ nodes (built on AWS: Lambda, EC2, EBS)
- Modernized deployment process using reproducible infra-as-code practices (Terraform, Ansible, Docker on AWS), eliminating frequent crashes and achieving 99% uptime

### Software Developer @ Ion Channel
Jan 2016 – Jan 2017 | Portland, Oregon, United States
- Built microservices integrations in Ruby/Sinatra for CI/CD pipeline to block builds with detected CVE vulnerabilities, supporting both AWS cloud and on-premises deployment for DOD customer

### Ruby Developer @ VanderHouwen & Associates
Jan 2013 – Jan 2014 | Vancouver, Washington, USA
- Developed a large Ruby on Rails app supporting 24/7 grid operations for Bonneville Power Administration, used continuously by ~14 operators across redundant control centers in Vancouver and Spokane
- Upgraded from Rails v2 to v4 and from Ruby 1.8 to 2, resulting in 36% faster app loads
- Rewrote core MySQL queries for critical grid management app using low-level Arel API, enabling future platform flexibility - successfully migrated to MS SQL Server after my departure


## Education
### Bachelor of Science - BS in Computer Science
East Central University


## Contact & Social
- LinkedIn: https://linkedin.com/in/nmarley
- Website: https://marley.io

---
Source: https://flows.cv/nathanmarley
JSON Resume: https://flows.cv/nathanmarley/resume.json
Last updated: 2026-03-29