# Upwork Job Posting ## Go-to-Market (GTM) Engineer – AI, Automation & Growth for Customs Brokerage (3-Month Contract) ### About Us We are a fast-growing U.S. Customs Brokerage and Trade Compliance firm looking to transform how importers find and work with customs brokers. Our vision is to become one of the most technology-driven customs brokerages in the United States by leveraging AI, automation, and data to improve customer acquisition, client experience, and operational efficiency. We are looking for an experienced **Go-to-Market (GTM) Engineer** who can combine software engineering, AI, sales automation, and growth strategies into scalable systems. This is **not** a traditional marketing position. You will be building technology that generates revenue. --- # Contract Duration **3 Months (with potential for long-term engagement)** Expected commitment: * 20–40 hours per week * Flexible schedule * Remote --- # Project Goals By the end of this contract, we want to have a repeatable system that: * Generates qualified importer leads * Automates outbound prospecting * Tracks and nurtures prospects * Uses AI to personalize communications * Integrates sales, marketing, and CRM workflows * Provides dashboards for business performance --- # Responsibilities You will design and build systems including: ### 1. Importer Lead Generation * Build databases of U.S. importers * Analyze import data * Score potential customers * Identify high-value prospects * Build workflows for ongoing lead generation --- ### 2. CRM & Sales Automation Integrate and automate platforms such as: * HubSpot * Pipedrive * Salesforce * Airtable * Notion Create workflows for: * Lead routing * Email sequences * Pipeline automation * Follow-up reminders * Customer lifecycle management --- ### 3. AI Sales Automation Build AI-powered systems that can: * Research prospects * Generate personalized cold emails * Draft LinkedIn outreach * Prepare sales call notes * Summarize meetings * Recommend follow-up actions Experience with OpenAI APIs, Claude, Gemini, or similar AI platforms is highly desirable. --- ### 4. Data Engineering Develop pipelines using: * Python * APIs * SQL * Web scraping (where appropriate and compliant) * ETL workflows Build importer intelligence databases that combine: * Company information * Import activity * Contact enrichment * Lead scoring --- ### 5. Business Intelligence Create dashboards showing: * Lead generation * Conversion rates * Sales pipeline * Revenue metrics * Customer acquisition cost (CAC) * Marketing ROI --- ### 6. Website Growth Recommend and implement tools that improve conversion, such as: * Interactive duty calculators * Customs compliance checklists * HTS lookup tools * AI chat assistants * Lead capture forms * Landing pages --- ### 7. Automation Automate repetitive business tasks using tools such as: * n8n * Zapier * Make * Python scripts * APIs --- # Technical Requirements Strong experience with several of the following: * Python * JavaScript/TypeScript * SQL * REST APIs * OpenAI API * LangChain or similar AI frameworks * HubSpot * Zapier * n8n * Make * Git/GitHub * Docker (preferred) * Cloud platforms (AWS, Azure, or GCP) * Web scraping * Data visualization --- # Nice to Have Experience in one or more of these industries: * Customs Brokerage * Freight Forwarding * Logistics * Supply Chain * International Trade * B2B SaaS Knowledge of: * U.S. Customs (CBP) * HTS Classification * ACE * Import/Export Compliance is a major advantage but not required. --- # Deliverables ## Month 1 * Understand business processes * Build CRM structure * Develop importer database * Set up AI workflows * Build first lead generation pipeline * Deliver initial dashboard *Launch automated outbound campaigns --- ## Month 2 * Build AI prospecting assistant * Create reporting dashboards * Integrate CRM automations * Develop customer scoring model --- ## Month 3 * Optimize workflows * Build additional AI tools * Document systems * Train internal team * Deliver production-ready automation stack --- # Success Metrics At the end of the contract we expect to have: * A scalable lead-generation engine * Automated outreach workflows * Centralized CRM * AI-assisted sales processes * Real-time reporting dashboards * Documented systems ready for long-term growth --- # What We're Looking For We value builders who enjoy solving business problems with technology. You should be comfortable working independently, proposing ideas, and delivering practical solutions rather than waiting for detailed instructions. If you've built growth systems that combine AI, automation, software engineering, and sales, we'd love to hear from you. --- ## To Apply Please include: 1. A brief introduction about yourself. 2. Examples of AI or automation projects you've built. 3. Links to GitHub, portfolio, or case studies (if available). 4. Your experience with CRM integrations and sales automation. 5. Your preferred hourly rate. 6. Why you're interested in this project.

Founding AI Agent & Automation Engineer Build a Personal AI Operating System for a Founder. Hi, I am looking for a highly capable AI Agent / Automation Engineer to help build a personal AI operating system that will eventually handle a significant portion of my day-to-day information, organization, research, preparation, and workflow management. This is not an Executive Assistant position nor a basic chatbot project. I am looking for a technical builder who can architect and implement an AI system using OpenClaw, a dedicated Mac mini, LLMs, APIs, MCP, automation workflows, memory, and secure integrations. The Goal The long-term vision is: Founder → AI Operating System → Information → Decisions → Approved Execution I want an AI system that can understand my business context, remember important information, monitor workflows, prepare work for me, surface things that need attention, and execute authorized actions. Phase 1 — Build the Foundation You will help me: Configure a dedicated Mac mini Install and configure OpenClaw Configure the OpenClaw Gateway Connect appropriate AI models Establish persistent services Design the AI's memory and context architecture Build secure tool access Configure MCP where appropriate Build API integrations Build automation workflows Establish logging and monitoring Create backups and recovery procedures Establish clear permissions and approval gates Phase 2 — Connect the Operating Environment The system should eventually be capable of securely working with business tools such as: Email Calendar Messaging Project management systems CRM GitHub Cloud storage Documents Business databases Analytics Internal applications Integrations must use legitimate APIs, approved authentication methods, and respect the Terms of Service and security requirements of each connected platform. Phase 3 — Build the AI Executive Layer Examples of what I ultimately want the system to do: Morning briefing "Give me everything I need to know today." The system should be able to identify: Important emails Upcoming meetings Outstanding commitments Project issues Follow-ups Deadlines Important business activity Information retrieval "Find everything we have discussed about this project." "What's still outstanding?" "What decisions have been made?" Preparation "Prepare me for tomorrow's meetings." "Summarize the latest activity and give me the key talking points." Workflow management "Create the follow-up tasks from this meeting." "Remind me if this hasn't been completed." Proactive intelligence The system should eventually identify issues before I ask: Stalled projects Missed follow-ups Upcoming deadlines Important unanswered messages Changes requiring my attention Recurring operational problems Founder Memory A major component will be building a structured memory system around: People Projects Decisions Priorities Documents Conversations Commitments Processes Preferences Historical context The objective is to dramatically reduce the amount of context I have to repeat. Required Technical Experience Strong candidates should have experience with several of the following: OpenClaw or comparable AI agent frameworks OpenAI / Claude / Gemini MCP AI agents and tool calling Python JavaScript / TypeScript REST APIs Webhooks OAuth n8n / Make / Zapier GitHub macOS Linux Docker Browser automation RAG / vector databases LLM memory architectures Agent orchestration Automation architecture Security and credential management Security Is Extremely Important This system may eventually have access to sensitive business information. You must understand: Least-privilege access OAuth API credential security Secrets management Permission boundaries Sandboxing Logging Backups Recovery Approval workflows Safe handling of external actions The system should not independently perform high-impact or irreversible actions without appropriate authorization. What I'm Looking For I want a builder, not someone who simply follows a setup tutorial. You should be comfortable: Reading documentation Debugging systems Writing code Working with APIs Designing architectures Troubleshooting integrations Thinking independently Explaining technical decisions clearly You should be able to take: "I want my AI to do this." and turn it into: architecture → integration → automation → testing → deployment. When Applying Please answer these questions: Have you built an AI agent that can actually interact with external tools or systems? Explain. What experience do you have with OpenClaw or comparable agent frameworks? Have you configured an always-on Mac/Linux AI environment? What is your experience with MCP? Show examples of AI automation systems you have personally built. How would you design memory for a personal AI operating system? How would you prevent an AI agent from taking an unsafe or unauthorized action? What would your architecture look like for this project? What is the most complex AI automation you have personally built? Please keep all pre-contract communication and proposal materials within Upwork. I am looking for someone who can start with the technical foundation and potentially become a long-term technical partner as the system evolves. If you have actually built agentic systems ( this does not mean experimenting with prompts ) LMK Id like to hear from you.

We're building an internal AI system that runs entirely on our own hardware (no cloud inference) against our own company data. We have a working proof-of-concept and want to get the architecture right. We need an experienced consultant to review what we've built, pressure-test our decisions, and tell us where we're wrong. This is an advisory/validation role first. We have someone doing the hands-on work; what we want is a senior second opinion to make sure we're building this the right way. NOTE: If you don't fully understand this job and you are just asking AI, don't apply. I will know if you are using AI to answer me on everything. I plan to do a thorough in person interview. What we're running today: Inference: RTX 5090 (32GB, Blackwell), Ubuntu 24.04, running llama-server (llama.cpp + CUDA) serving Gemma 4 31B-it (Q4_K_M GGUF) at a 262,144 context window. Also hosts our MCP retrieval server, PostgreSQL, and Qdrant. Embeddings: separate machine with an RTX 3060 running vLLM serving Qwen3-Embedding-4B. RAG: hybrid retrieval — Postgres full-text search + Qdrant semantic search with RRF fusion, exposed through a custom MCP server with tool-calling. Data: ingesting our own internal operational data into Postgres + Qdrant. Planned stack: LiteLLM for model routing, n8n for automation, Open WebUI for the interface, Langfuse for observability, Vault or Infisical for secrets, Keycloak/Azure AD for SSO. What we need help with: Validating our two-machine split (inference vs. embeddings) and whether our VRAM/context budget holds up under real load, specifically whether a 256K context window is real and performant on a single 32GB card or just nominal. Model selection and routing strategy: which open-weight models for which tasks, and how to structure LiteLLM routes. RAG quality: chunking, embedding dimensionality, hybrid search tuning, reranking and making retrieval actually accurate on messy real-world data. Sanity-checking our overall architecture and telling us our blind spots. You should have done: Stood up local LLM inference in production with llama.cpp/llama-server and vLLM, not just Ollama on a laptop. You understand GGUF quantization (Q4_K_M, IQ-series), KV cache, KV-cache quantization, and how context length maps to actual VRAM consumption. Real fluency in GPU sizing math given a model, a quant, and a context window, you can tell us whether it fits on a given card and what throughput to expect. Bonus if you've worked with Blackwell / sm_120a. Built production RAG vector DBs (Qdrant, pgvector), hybrid search, RRF fusion, embedding model selection, reranking, evaluation. Worked with agentic/tool-calling systems and ideally MCP servers. Know the open-weight model landscape (Gemma, Qwen, Llama, Mistral, Phi, Nemotron, Hermes) and their licenses well enough to advise. Production ops: systemd, Docker, model gateways (LiteLLM or similar), observability (Langfuse), secrets management, SSO.

I'm looking for someone experienced with **n8n** to help me re-record **4 course tutorial videos** for my program. I already have the original/reference videos completed, so you will **not need to create the automations from scratch or figure out what to teach**. The reference videos are 30min total so should be super easy ### What You'll Be Doing I will provide you with: * 4 reference videos (**approximately 30 minutes total**) * The JSON files for each n8n automation Your job will be to: 1. Watch the reference video for each automation. 2. Upload/import the provided JSON file into n8n. 3. Screen record yourself explaining how to set up the automation. 4. Follow the reference videos as closely as possible—you can essentially copy the explanation and walkthrough. These are straightforward **course tutorial recordings**, not complex automation development. ### Requirements * Experience using **n8n** * Comfortable importing and working with JSON workflow files * Able to clearly explain technical steps in English * Able to screen record high-quality tutorial videos * Good microphone/audio quality ### Important You do **not** need to create new automations or come up with your own training material. The reference videos already show exactly what needs to be done. I'm looking for someone who can follow the existing tutorials, recreate the setup process, and clearly explain the steps while screen sharing. Please include your experience with **n8n** and any examples of tutorial or screen-recording work you've done. This should be a relatively quick and straightforward project for someone familiar with n8n.

We need an Automation specialist to help build and optimize an automation pipeline for our business. The work includes setting up integrations, creating reliable workflows, and improving existing processes. You should be comfortable with troubleshooting issues, testing automations, and making recommendations for better efficiency. This is a part-time project for someone who can communicate clearly and deliver dependable automation solutions.

I'm looking for an automation expert to build an n8n workflow for me. It's not overly complex. Using various tools to scrape online data, clean/format it, use Claude to analyze it, export it, etc. Is that up your alley? If so, do you have availability to complete it this week? - Let's talk Jeff

"I built an automated inventory monitoring system using n8n, Google Sheets, and Google Gemini. The workflow runs weekly, checks stock levels against predefined thresholds, and detects low-stock items automatically. When inventory falls below the limit, the system aggregates affected products and sends a structured alert via Gmail. This automation prevents stockouts, reduces manual checks, and improves purchasing efficiency."

I have a client that is looking to create an automated workflow that will search (likely Trepp) for real estate debt maturities. We then want to contact the borrower to schedule calls about purchasing the property from them. I need a cost to build the agent and what it would cost to monitor it on a monthly basis.