Enterprise Product → Hands-on AI Deployment → Forward-Deployed Engineering

I turn complex enterprise workflows into practical AI systems.

I’m Rebecca Li, a product manager moving into Forward-Deployed AI and hands-on AI deployment. I work at the intersection of enterprise workflows, solution architecture, local LLMs, agents, APIs, evaluation, and rapid prototyping — translating ambiguous business problems into systems that can actually be tested, deployed, and used.

About me

Business depth + technical execution

My background is in product management and complex enterprise systems, including commodity trading, pricing, risk, settlement, finance, supply chain, approval workflows, and operational platforms. That experience trained me to understand messy real-world workflows, stakeholder constraints, dependencies, and the difference between a good demo and a system people can actually operate.

I’m now deliberately building the engineering depth required for Forward-Deployed AI roles: Python, APIs, local model deployment, agents, tool calling, AI application architecture, document AI, speech AI, evaluation, and deployment troubleshooting.

I use public projects to demonstrate the complete FDE loop: discovery → technical scoping → architecture → prototyping → debugging → evaluation → deployment thinking.

What I bring

Why my background fits FDE work

Enterprise Domain DepthTrading · finance · settlement · operations
Customer & Workflow DiscoveryTurning operational problems into product scope
Hands-on AI SystemsLLMs · agents · tools · APIs · local deployment
Cross-functional DeliveryBusiness ↔ product ↔ engineering translation
Current positioning

Forward-Deployed AI / AI Product & Deployment Builder focused on enterprise workflows, agent systems, and practical deployment.

Featured deployments & case studies

Evidence of how I scope, build, debug, and deploy.

These projects are selected to demonstrate the exact capabilities required in Forward-Deployed AI: customer problem framing, technical scoping, solution architecture, hands-on implementation, deployment troubleshooting, evaluation, and enterprise domain understanding.

Claude Code CLI
      ↓
Local Proxy
      ↓
Ollama
      ↓
Qwen 27B Q3
LLM DeploymentAgent RuntimeDebugging

Can a 24GB MacBook run Claude Code with Qwen 27B?

Testing whether a consumer Mac can run a usable local coding agent — not just load a language model.

Local Agent
  ├─ safe_file_editor
  └─ safe_bash
        ↓
Qwen / Ollama
Agent SafetyTool CallingLeast Privilege

Building a safer local AI agent with controlled tools

Designing a local agent that can operate on files and shell commands while restricting unsafe paths and destructive actions.

Trade
  ↓
Pricing / Risk
  ↓
Allocation / Payment
  ↓
Settlement / Invoice
  ↓
AI Assist / Automation
Enterprise AIWorkflow DesignDomain

Designing an AI-native commodity trading workflow

Mapping where AI agents, recommendation systems, document AI, and automation can create value across a real trading lifecycle.

KYC → Orders → Pricing
      ↓
Allocation → Delivery
      ↓
Payment → Settlement
      ↓
Risk → Audit
Enterprise ProductCommodity Trading

End-to-end commodity trading platform

Designing a complex enterprise platform spanning customer onboarding, trading, settlement, logistics, finance, risk, and operational controls.

PDF / Image
     ↓
OCR / API
     ↓
Parse / Validate
     ↓
Structured Business Data
Document AIAutomationReliability

OCR-to-structured-data business automation pipeline

Turning unstructured documents into validated business data through OCR, APIs, parsing, retries, and structured extraction.

DeepSeek Harness
      ↓
Cordis Tool Layer
      ↓
Safe Tools
      ↓
Local Qwen Agent
Agent FrameworkRuntimeTools

Lightweight local agent runtime with Qwen

Exploring how model size, token limits, tool registration, and runtime architecture affect local agent reliability and performance.

View all 10 projects →
Flagship FDE case study

24GB MacBook + Qwen 27B + Claude Code

A systems-level experiment showing why “the model fits in memory” and “the agent is usable” are two very different engineering questions.

Customer-style question
Can a normal 24GB MacBook run a local coding agent capable of practical file and shell operations?
Scope
Chat, file read, file write, Bash execution, multi-turn behavior, context stress, latency, and runtime compatibility.
Architecture
Claude Code CLI ↓ Anthropic-compatible local proxy ↓ Ollama ↓ Qwen 27B Q3
Key failure
Real agent requests exceeded a 32K context window, showing how system prompts and tool schemas can become deployment bottlenecks.
FDE lesson
The bottleneck was not only model capability. System design, protocol compatibility, tool overhead, and operational constraints determined usability.
90-second recruiter demo

Show outcome before detail

Embed demo video here
Problem → architecture → live action → result
Evidence checklist

Deployment scorecard

ChatTEST
Read local fileTEST
Edit fileTEST
BashTEST
5-turn agent taskTEST
Context stress testTEST
Forward-Deployed capabilities

The skills I’m building around the FDE delivery loop.

My goal is not to present isolated technologies, but to show the full set of capabilities required to move from a customer problem to a working AI deployment.

01 · Customer discovery & technical scoping

  • Workflow mapping
  • Problem framing
  • Use-case prioritization
  • Requirements & constraints
  • Cross-functional communication

02 · AI systems & agents

  • LLMs & local LLM deployment
  • Agent workflows
  • Tool calling
  • Context management
  • Prompt / system design
  • RAG fundamentals

03 · Hands-on engineering

PythonREST APIsJSONGit / GitHubSQLSupabasePostgreSQLOllama

04 · Deployment & integration

  • Local model serving
  • API integration
  • Cloud deployment basics
  • Runtime troubleshooting
  • Authentication / parsing / retries
  • Performance trade-offs

05 · Evaluation & reliability

  • Functional test design
  • Latency & context testing
  • Failure-mode analysis
  • Output validation
  • Safe tool access
  • Deployment readiness thinking

06 · Enterprise domain expertise

  • Commodity trading
  • Pricing & exposure
  • Settlement
  • Finance / accounting workflows
  • Supply chain
  • Risk & controls
Certifications & continuous learning

Structured learning, connected to real projects.

Certifications are supporting evidence — each credential is paired with the skills it developed and the projects where those skills are being applied.

AI Foundations

Introduction to Artificial Intelligence (AI)

Coursera / IBM
AI FundamentalsML Concepts
Applied inAI product architecture · enterprise AI use-case design
Generative AI

Generative AI: Introduction and Applications

Coursera / IBM
Generative AIFoundation ModelsLLMs
Applied inLocal LLM experiments · AI IELTS Tutor · enterprise AI workflow
Prompt Engineering

Start Writing Prompts like a Pro

Coursera
Prompt DesignStructured Interaction
Applied inAgent workflows · IELTS feedback loops · AI content systems
Python

Python for Data Science, AI & Development

Coursera / IBM
PythonAPIsData Processing
Applied inOCR pipeline · English AI app · agent experiments
LLM Engineering

Generative AI Engineering / LLM Learning Track

Coursera / IBM · ongoing
TransformersHugging FaceRAGAgents
Applied inLocal Qwen deployment · Claude Code integration · agent runtime work
More credentials

Full Coursera Certificate Portfolio

Credential library

Add your complete verified Coursera credential links here once finalized.

Before publishing, replace any “ongoing” or inferred course titles with your exact Coursera credential names and credential URLs.
Professional experience

Enterprise product experience is the foundation of my FDE profile.

1
Enterprise Product ManagementDesigning complex business systems across trading, finance, supply chain, settlement, risk, and operations.
2
Workflow & stakeholder discoveryTranslating operational pain points, controls, approvals, and business constraints into system requirements and product workflows.
3
AI product prototypingBuilding AI applications, agent workflows, OCR pipelines, knowledge systems, and local model experiments.
4
Hands-on AI deploymentMoving deeper into model serving, APIs, tooling, context management, runtime debugging, safety, and evaluation.
5
Forward-Deployed AITarget role: combine domain depth, customer discovery, hands-on engineering, and deployment ownership.
Let’s connect

Building or hiring for enterprise AI?

I’m especially interested in Forward-Deployed Engineer, Applied AI, AI Deployment, and AI Product roles where deep customer workflows and hands-on technical execution meet.

Replace placeholders with your real profile links before publishing.