Title: Backend Developer — AI Data Pipeline, Vector DB & Real-Time Push API Post: We are building an automated backend system that continuously crawls public web sources, processes and indexes content using AI, and delivers updates via webhooks. Looking for someone who has built this type of system before and can move fast. NDA required before project details are shared. What you’ll build: • Web crawler network —. • AI processing pipeline — cleans, deduplicates, chunks, and embeds ingested content into a vector database using an LLM embedding model. Quality scoring and incremental updates required. • Push API — monitors for significant content changes and delivers updates via webhook endpoints automatically. Includes configurable push schedules per subscriber, REST query endpoint, API key authentication, and token usage tracking per key. Tech stack (flexible — use what you know best): • Python (FastAPI) or Node.js • Any vector DB — Pinecone, ChromaDB, Supabase • Any LLM API — Anthropic or OpenAI • Any scheduler — n8n, APScheduler, cron • Redis for queue management • Railway, Render, or AWS for deployment Requirements: • NDA signed before kickoff — non-negotiable • Must have built RAG pipelines or vector DB systems in production — not tutorials • Must have experience with web crawlers and scheduled job pipelines • Must have experience with webhook delivery systems • GitHub or portfolio showing relevant deployed work required • 95%+ Job Success Score preferred • Individual contractors only — no agencies To apply include: • Example of a similar system you’ve built — web crawler, RAG pipeline, or push notification API • Your preferred stack for this type of build • Brief technical approach in 3–5 sentences • Hourly rate and availability to start Budget: $50–$80/hr Timeline: 3 weeks — focused sprint with daily check-ins

We are looking for an experienced AI automation developer to build a private executive assistant named Jarvis for a business owner named Vince. Jarvis must operate as a professional, respectful, fast-moving executive assistant. The assistant will communicate with Vince through iMessage, access his Google Calendar, remember important information, send meeting reminders, and maintain local files/data on an office iMac. This is not a basic chatbot. We need a working AI assistant that can hold real conversations, remember context, anticipate needs, and protect Vince’s time. Core Requirements The assistant must: Communicate with Vince through iMessage on macOS. Store all data, memory, and files locally on the office iMac. Access Vince’s personal Google Calendar. Send Vince a message 20 minutes before meetings. Remember meeting times, preferences, important facts, and prior conversations. Use context from previous messages and stored memory. Start conversations professionally with: “Hello Sir. What do you need today sir.” Maintain a direct, respectful, professional tone. Avoid fluff, long explanations, repetition, and unnecessary questions. Understand that Vince has zero tolerance for wasted time. Validate Vince’s instructions and respond with useful answers quickly. Ask onboarding questions at first launch to learn Vince’s occupation, goals, priorities, communication preferences, daily routines, and assistant expectations. Be built in a way that can expand later into email, task management, document handling, and proactive reminders. Important Personality / Communication Rules Jarvis must be designed around Vince’s communication style: Direct. No fluff. No jargon. Lead with the answer. Never ask for information Vince has already provided. Protect his time, brand, relationships, and workflow. Jarvis should function as an executive personal assistant whose purpose is to remember everything so Vince does not have to repeat himself. Technical Scope The developer should be comfortable with: macOS automation. iMessage / Messages.app integration. Google Calendar API. Local file storage and local memory architecture. AI agent frameworks. Cron jobs or scheduler-based reminders. Secure credential handling. Local database or file-based memory. Python, Node.js, or similar automation stack. Optional: BlueBubbles, AppleScript, Shortcuts, SQLite, vector database, local LLM tools, OpenAI API, Claude API, or similar. There is already a macOS/iMessage path available using CLI-based message tooling, but we are open to the developer recommending the best reliable implementation. Existing iMessage automation concepts include sending, reading, and watching message history through macOS Messages.app tooling. Deliverables We need the developer to provide: Working Jarvis assistant installed on the office iMac. iMessage communication with Vince. Google Calendar integration. Automatic 20-minute meeting reminders by text. Local memory system. Local file/data storage structure. First-run onboarding question flow. Prompt/personality system for Jarvis. Basic admin documentation showing how to restart, update, and maintain the assistant. Security notes for credentials, permissions, and local storage. Testing checklist proving iMessage, memory, reminders, and calendar sync work. First-Run Intro Flow Jarvis should text Vince an introductory message and ask important setup questions such as: What is your primary occupation? What are your top business priorities right now? What meetings or events should I always remind you about? Who are your key contacts? What should I never interrupt you for? What should I always notify you about? What tone do you prefer from me? What daily reminders would make your life easier? What are your current goals for the next 30, 60, and 90 days? Ideal Candidate The ideal freelancer has built AI agents, personal assistants, calendar bots, local automation tools, or macOS/iMessage workflows before. We want someone practical who can build a reliable working system, not just create a demo. Please include: Similar AI assistant or automation projects you have built. Your recommended tech stack. How you would connect iMessage. How you would handle local memory. How you would secure calendar credentials. Estimated timeline. What you need from us to start.

I’m running a real estate investment platform called ToInvested.com. The project is about 90% finished, and most of the code was built with Claude together with another engineer. Now I need a senior engineer to step in, review the full product carefully, test every major workflow, and help verify that everything is working correctly before it goes live. This is not just a “write more code” role. I need someone who can look at the platform like a real product, find hidden bugs, catch weak logic, test edge cases, review the AI-generated code, and tell me honestly what is ready and what still needs fixing. Because this is a real estate investment platform, accuracy and trust matter a lot. Users may rely on property data, investment logic, calculations, and AI-driven insights, so even small issues can create a serious problem later. The ideal person has strong full-stack experience, understands AI-assisted development, and has a good testing mindset. Real estate tech experience would be a big plus, especially with property platforms, investment tools, marketplaces, mortgage systems, or financial workflows. My main goal is simple: I want someone to break the project before real users do. If you’re the kind of engineer who can take a nearly finished product, test it deeply, clean up weak areas, and help make it production-ready, I’d be happy to talk.

With all the advancements in ai, I dont need a coder but someone who knows how to run multiple Ai platforms so as to execute business plans for new ventures

We’re a product-focused team developing an AI-driven SaaS platform aimed at improving how businesses handle information, workflows, and internal processes. We’re looking for a developer who can build a smart feature that allows users to interact with their data and documents in a more automated and intuitive way. The goal is to reduce manual effort and enable faster, more informed actions through AI. This role involves designing and implementing the core logic behind the feature, connecting AI capabilities into the product, and ensuring everything works smoothly within the existing system. You should be comfortable building end-to-end functionality, working with modern web applications, and integrating AI services into real user-facing features. Experience with AI-powered products, automation tools, or data-driven applications is highly relevant.

We are building a next-generation workflow automation platform that combines deterministic business rules, artificial intelligence, document intelligence, and human review workflows into a single operating system. This is not a traditional CRM project. Our vision is to develop a doctrine-driven platform where business rules serve as the system authority, AI serves as an analytical and drafting layer, and human reviewers serve as the final compliance checkpoint. We are seeking an experienced engineer or engineering partner who can help architect and build the platform from the ground up. Project Objectives The platform will: • Ingest and analyze large volumes of structured and unstructured documents • Extract data from reports, PDFs, and supporting documentation • Apply rule-based workflow logic • Generate AI-assisted recommendations and draft outputs • Maintain complete audit trails and workflow transparency • Route work through human review checkpoints • Support future deployment of local AI infrastructure for privacy and performance Core Architecture The system will be built around four primary layers: 1. Rules Engine * Deterministic business logic * Workflow orchestration * State management * Trigger and escalation logic * Audit tracking 2. AI Layer * Document analysis * Classification * Pattern detection * Summarization * Draft generation * Structured outputs 3. Local Processing Layer * OCR * Document parsing * Data extraction * Vector search * Local inference capabilities * Privacy-first processing 4. Human Review Layer * Quality assurance * Workflow approvals * Compliance review * Exception handling Initial Development Priorities Phase 1 • User authentication • Client record management • Document upload system • OCR and document extraction • Workflow engine • Rule-based status management • Review dashboard Phase 2 • AI-powered document analysis • Automated classification • Recommendation engine • Draft generation workflows • Response parsing Phase 3 • Local AI infrastructure • Vector database integration • Knowledge retrieval system • Multi-agent workflow orchestration • Advanced automation Desired Technical Experience Required • React / Next.js • Node.js, Python, or similar backend framework • PostgreSQL or equivalent relational database • REST APIs • Cloud infrastructure (AWS, Azure, or GCP) • Workflow automation systems • Document processing pipelines Preferred • OpenAI APIs • Anthropic APIs • Retrieval-Augmented Generation (RAG) • LangGraph, LangChain, or similar frameworks • Vector databases • OCR technologies • AI agent architectures • NVIDIA AI ecosystem • Local model deployment What We Are Looking For We are not looking for someone who simply builds forms and dashboards. We are looking for a builder who understands how to combine: • Rules engines • Artificial intelligence • Workflow automation • Human review systems • Scalable software architecture The ideal candidate enjoys solving complex business process problems and translating expert decision-making into software systems. Engagement Structure Open to: • Fractional CTO • Lead Architect • Senior Full-Stack Engineer • AI Systems Engineer • Development Agency • Long-term strategic technology partner To Apply Please provide: • Relevant project examples • Experience building workflow automation platforms • Experience with AI-powered applications • Technology stack recommendations • Estimated availability • Preferred engagement structure

## Project Overview I am seeking an experienced Senior AI Systems Architect / Full-Stack Engineer to evaluate and potentially lead the technical architecture of a new enterprise software platform currently under development. At this stage, I am not looking for someone to simply write code. I am looking for an experienced technical professional capable of evaluating architecture, recommending technologies, and helping define the engineering roadmap for Version 1. The project involves the integration of artificial intelligence, enterprise software architecture, workflow automation, secure data management, API integrations, and cloud-based application design. Because the project contains proprietary intellectual property, detailed information will not be disclosed during the initial interview process. Candidates selected to move forward will be asked to execute a Non-Disclosure Agreement before reviewing project documentation. ## Initial Objectives • Review the existing project at a high level. • Evaluate technical feasibility. • Recommend the most appropriate technology stack. • Design the production architecture. • Develop an implementation roadmap. • If mutually agreed, continue as the lead software architect for Version 1. ## Required Experience Applicants should have significant experience with: • Enterprise software architecture • Artificial Intelligence integration • API development and integration • Full-stack application development • Cloud architecture and deployment • Database design • Authentication and application security Excellent communication skills are important. I am looking for someone who enjoys solving complex architectural challenges and who is interested in building something from the ground up. ## Please Include 1. A brief summary of your architecture experience. 2. Examples of enterprise software systems you have helped design. 3. AI-related experience. 4. Your preferred technology stack. 5. Why this opportunity interests you. The initial engagement is intended as an architectural evaluation. A longer-term relationship may develop if there is a strong mutual fit.

I am working through a design agency on an application for their end client. I think the agency will need you to contract with them directly, but I will manage the project for them. I have scoped out the project already, and our plan is to internally perform a design phase with the client to produce a prototype with Lovable. There may be minor changes to scope after that design phase. The purpose of the app is to create bespoke wedding gown concept images for potential customers of an online wedding dress store. I have provided the details below and attached as a PDF 1. Customer opens an AI dress/gown design experience from a link in their separate e-commerce site. - This can be presented in its own page, we don't want a chat window to be present on any other page - This will be a chat-based interface built into the content area of the page, instead of a popup - The design must be elegant, and match the theme of the e-commerce site - The top navbar and footer don't need to be exactly recreated in this subdomain site, but should look similar enough to create a seamless experience - There will be no integration with the e-commerce site, we need to keep these web apps completely separate 2. The customer must sign up for an account and purchase one credit to begin the AI session - We will need to set up the subdomain site with its own payment processing system and login system - The payment integrations are Stripe to facilitate credit card and Apple pay, and a basic Paypal integration 3. The customers should be able to use a magic link to sign into their accounts, instead of having to remember a password - The account should automatically remember the browser to reduce friction for future access to the app 4. When an AI session begins, we will ask the customer a series of questions programmatically to prime the AI agent so that it can deliver better results - The questions will need to use conditional logic, such that the first question which determines one of 3 main conditional tracks: What type of gown are you looking for? Wedding Gown, Evening Gown, Cocktail Dress - If Wedding Gown is selected, the AI should suggest for the customer to take go to a bridal store and pictures of themselves in different dresses they like and upload the pictures, and describe what they do and don’t like about each dress. It can ask this in the freeform chat, since it may make the most sense to let them fill out the entire questionnaire to stay engaged, and we should reduce the costs of development for the questionnaire by omitting any unnecessary UI that the freeform chat can provide. - It may be best to always just prompt for them to upload the inspirational image at the beginning of the freeform chat so we can omit unnecessary programmatic UI, but in the case of the Wedding Gown it will specifically ask the customer to peform the above task. - We may have other specific questions to add to the questionnaire depending on what conditional track the customer chooses, though only the 3 main branches of conditional logic based on dress type will be required. - Examples of general questions it will need to ask are as follows: -- silhouette -- neckline -- sleeves -- fabric -- embellishments -- color -- train -- length -- closure -- lining -- structure -- inspiration -- event type -- I didn’t get the exact list of questions yet from my client that we should ask in the initial questionnaire. Let me know if you will need this information to accurately provide a price for the development of this application 5. We should not display a concept image after the programmatic questionnaire, the customer will be taken directly into the freeform chat from the questionnaire. - The AI agent may start with an overview of the selected choices from the questionnaire, then can generate concept images at its discretion. 6. The AI should guide the customer through a freeform conversation - The conversation should begin with the AI asking the customer to subjectively describe their dream dress 7. The AI should also make a suggestion near the beginning of the conversation for the customer to upload at least one inspirational photo, but photo upload is optional - If the customer uploads an initial inspiration image, the AI agent should not attempt to figure out body type, measurements, or any other information that we can gather programmatically. - It should treat the inspirational image the same way it would treat any image the customer uploads during the freeform chat, to reduce the cost of development as much as possible. 8. Customer can proceed with a freeform conversation description - The customer should have the option to type in a chat and to upload images - The purpose of the conversation is for the customer to describe the desired dress or gown in an open-ended way 9. AI generates one or more concept images based on the conversation, as soon as it can once it has enough information - The AI model we select should be very good at generating these types of images, this is probably the most important quality the AI model needs to have - The concept images should have the same quality as the final image 10. It is acceptable to generate the gown on a mannequin or a real human model, however the dress must be photorealistic, not a sketch or cartoonish rendering. 11. The concept images that the AI generates and the final image should portray the body type and skin color which the customer specifies - It is very important for us to render the image of the garment on the correct body type - ex. Hourglass, pear-shaped, thin, plus sized, etc. -- Specific body measurements do not need to be factored into the rendering of the body type, it just generally needs to be able to render the garment on different body types. - It is also very important for us to render the garment on a human model or mannequin which has the same or similar skin color as the customer inquiring -- This is important for the customer to judge the garment color and fabric type that will look best on them -- This is also important to make the app inclusive for people of all racial backgrounds who might use the app -- It may be best not to display the face, or if human models are used, to use pictures of models with different racial backgrounds, to avoid bizarre mismatches between facial characteristics and skin tone - The AI agent should ideally prioritize pictures of garments from our client’s website to use as inspiration when it generates renderings in the freeform conversation, along with the customer’s description of what they want. However this is not a hard requirement, so it could be eliminated from the requirements if it greatly increases devlopment effort. - The requirement for the quality of the images that are generated will be somewhat subjective and so we will need to budget time for our client to request revisions to this based on their review of the system. - We need to build the image generation part upfront to ensure the quality is acceptable before we spend time on other parts of the application. 12. AI asks whether the generated concept is generally what the customer wants - Customer can revise the concept conversationally 13. AI can regenerate or refine images after customer feedback 14. The tone of the conversation the AI has with the customer is important. - We will want it to speak like a friendly expert seamstress. - This requirement will be somewhat subjective and so we will need to budget time for our client to request revisions to this tone based on their review of the system. 16. We ideally want the agent (both chat and image generation) to have deep expertise about fabrics and these types of garments in general, so it can guide the user through prompts, and render the chosen fabrics correctly - I think freeform chat will be necessary for the customer to explain which fabrics should be used where on the garment, instead of gathering this informaton in the programmatic questionnaire - The customer will likely revise the fabric selections after they see the initial renderings of the garment - We would like to avoid the costs of training an AI for this, so ideally we should use commercially available AI models which have been trained for this purpose, instead of having to train our own model. Prompting the AI with this information might be a cost-effective way to teach it this expertise 17. There will be certain restrictions on what types of colors or fabrics can be used in the dress designs - So, the agent should know these restrictions when it has the freeform conversation with the customer. - For example, the store owner will not be able to produce dresses with neon colors, tie dye colors, etc. - Our client will articulate a list of restrictions for us before we begin the project. 18. AI should never display links to other websites, or suggest for the customer to navigate to other websites 19. This AI might not need to be trained specifically for this industry, but we should at least use prompting to direct it to gather this kind of information, and to give it some background about what each of these things mean, so it can describe them to the customer. We basically need to make it as knowledgable as possble while keeping costs low. 20. The AI system the system should remember their active conversation - Since the customer will be required to have an account to use the AI system we can use that to automatically save the AI conversation - The saved conversation should preserve all the information that the customer input since the beginning of the AI session - A customer can only have one active AI session at a time - The customer cannot resume an AI session that has been completed - We don't need to provide a way for the customer to see the details of completed AI sessions 21. AI should have a fallback/human-help option if the customer gets stuck or the AI fails. - The fallback should collect enough information for an admin to follow up manually, so it should present a form in order to ensure that all the necessary information gets collected - A message should be displayed above the form, or somewhere on the page, to inform the customer that the entire conversation will be sent along with the form submission, so they know that they do not have to type all the details of the AI conversation - The app must present a button outside of the chat prompts after 3 - 5 chat messages have been sent, so the customer knows they have the option to terminate the AI conversation and manually ask for help. - That button would display the form - We don't want to display the button before any conversation has happened because we don't want customers to skip the chat altogether. -- One of the business goals of this app is to allow custom inquiries without overwhelming the support staff - Site admins must have the ability to adjust how many messages the button will display after, so they can control this threshold after they observe the results of real conversations - After the button initially displays, it should remain present in the view so the customer can easily access it at any point in the conversation 22. The freeform chat must be limited to something like 50 to 75 messages, in order to avoid excessive charges from the 3rd party AI services - This threshold should be adjustable from an admin portal - If this threshold is reached during the conversation, then we should force the customer to use the fallback form from requirement #21 to submit their inquiry 23. Customer can submit the completed design inquiry when satisfied. - During the submission process, the chat must ask for the following information, and present the following pre-written messages. This doesn't actually need to be executed by the AI model, but it can just be programmatically presented to the customer: - Ask for customer contact info, including name, email, and phone number. - Ask for requested event/date, while making clear the date is not guaranteed. - Ask for seamstress-relevant measurements, including bust, waist, hips, hollow-to-hem, shoulder width, bust point, underbust, waist-to-floor, arm length, bicep, wrist, back width, torso length, height, shoe height, and preferred fit. -- I still have to refine this list with the client, I am not sure if it needs to ask for all these things, or if there are some different things that I haven't listed here which it needs to ask for -- When it asks for this information it should display links under each measurement type to articles which describe how to produce each of the measurements. We can hardcode these links or allow the admin to specify each, they don't need to be generated by AI. - Prewritten disclaimer text should display. 24. The final submission should notify a list of email addresses set by a site admin. 25. The final submission will completely consume the credit used to purchase this AI session - The AI conversation cannot be resumed after the final submission - Another credit must be purchased to start a new AI conversation - New AI conversations will not have any memory of the previous conversations, any new AI conversations will start from a clean slate 26. Admins must have the ability to manually reset a credit, or assign a credit for free and cancel a current session, so the customer can start a new AI conversation. - This doesn't need to be very user friendly for the admin. If a session is reset this way, no knowledge of the previous conversation needs to be preserved. 27. Admins should be able to review partial, or completed conversations within a list in the admin portal - Each line item should display a status indicator to show if the conversation has been submitted yet, if an admin has began the review process, or if the item has been handled: Ex. In Progress, Submitted, In Review, Awaiting Payment, Handling, Ready To Ship, Closed - Admin should be able to see the answers to the programmatic questionnaire - Admin should be able to review the full conversation history - Admin should be able to review all uploaded photos/files - Admin should be able to review all AI-generated images, and the final one should be clear to them - Admin should be able to see the collected technical design details and measurements 28. Pricing of the garment remains manual and is handled by after review, the AI should not give any quote or present any pricing even if asked by the customer. 29. If the customer asks for pricing, the AI should display a prewritten script like this: "Pricing will be determined by the store owner after this conversation has been reviewed." 30. Invoices and payment will be handled manually through native WooCommerce custom order/invoice functionality which is already present in the e-commerce site, the AI system doesn't need to handle this at all. I mentioned this above on the requirements, but I want to reiterate since it is important and a hard requirement for how the development milestones must be structured: - The requirement for the quality of the images that are generated will be somewhat subjective and so we will need to budget time for our client to request revisions to this based on their review of the system. - We need to do the image generation part upfront to ensure the quality is acceptable before we spend time on other parts of the application As an optional add-on to the scope of this project, can you give a separate estimate to enhance the AI such that it understands which kinds of modifications will increase or decrease the cost of producing the gown, so it can guide the customer in case they are asking for very expensive things. - It shouldn’t give any specific price numbers, but should give the customer guidance if additions or alterations will significantly increase or decrease the cost of production. - This will be to prevent the customer from being surprised when the store owner manually follows up with them with the price of the garment they designed. This client did agree to adhere to a strict schedule to provide feedback after each round of development, given that we complete each round of development on the schedule we agreed to. - However, this client has deviated from agreed schedules multiple times in the past on other projects I did with them, so you should factor that into your timeline and cost estimations - We cannot increase the development cost mid-way through the project, however we can adjust the development timeline if the client deviates from the schedule In your proposal, please also include a quote or estimate for the cost of hosting and ongoing maintenance after the app has launched - Our client can pay for the hosting directly - We will need at least ongoing updates to patch security vulnerabilities and ensure uptime of the app and all its features which will be defined by the scope of this project - We don't need a 100% 24/7 uptime SLA, but basically just keeping everything up to date so it stays stable, and we'd need someone to respond to outages within 24 hours - Outage response can consist of simple rollbacks, if necessary, as long as all the chat session info is at least provided to the client as a CSV or similar, along with all graphic assets from any conversations, so they don't lose any data from an outage - I would set the expectation with my client that we would treat any future support or enhancement requests to be additionally charged for on an as-needed basis

ElevenLabs Conversational AI Expert — Long, Multi-Node Voice Agents with Tool Calls Project type: Hourly Experience level: Expert Duration: Short-term engagement with potential for ongoing work About the project We're building voice agents on ElevenLabs Conversational AI (Agents Platform) that run long, complex calls of 20+ nodes in the workflow builder, with multiple tool/function calls along the way. The agent is embedded directly into our app (using the ElevenLabs SDK) rather than the ElevenLabs widget. The agents work, but we're fighting duplicate questions/answers. The agent re-asks questions it already asked, or repeats information it already gave, at different points in the call. We need someone who has actually built and shipped long-running ElevenLabs voice agents (not just simple single-prompt bots) to help us fix the structural setup so calls stay coherent end to end. That covers workflow/node architecture, state handling, prompt design, tool orchestration, and our client-side integration. What you'll do ● Audit our current agent: workflow node structure, system/node prompts, tool definitions, and conversation flow. ● Audit our client-side integration (the ElevenLabs SDK embedded in our app): session/connection handling, event handling, client tools, and how local app state stays in sync with the conversation. Reconnects, double-fired events, or repeated client-tool calls can also cause re-asks. ● Diagnose the root causes of the duplicate question/answer behavior. Possible culprits include context/state not being tracked across nodes, overlapping node responsibilities, prompt ambiguity, retrieval/knowledge-base issues, or client-side state/event problems. ● Redesign the node graph and transitions so each node has a clear, non-overlapping job and the conversation can't loop or re-ask. ● Improve state/variable management across nodes: dynamic variables, captured data, and how it's passed forward so the agent "remembers" within a call. ● Tighten tool/function calling: when tools fire, how results are handled, error/timeout handling, and avoiding redundant calls. ● Address context-window and long-call degradation, plus turn-taking behavior that causes drift. ● Recommend the right structural patterns for flows this long (single agent vs. multi-agent/agent transfer, sub-agents, branching). ● Document the fixes and the patterns so our team can maintain and extend the setup. You're a strong fit if you have ● Demonstrable hands-on experience with ElevenLabs Conversational AI / Agents Platform. Please reference specific agents or projects you've built. ● Experience with the workflow/node builder for branching, multi-step calls, not just a single system prompt. ● Experience embedding ElevenLabs in a custom app via the SDK (React/JS, WebRTC/WebSocket), not just the drop-in widget. ● Solid grasp of tool/function calling (client tools and server tools/webhooks), including error handling. ● Strong prompt engineering for voice, plus understanding of LLM context windows, state, and conversation memory. ● Experience debugging long conversations for looping and repetition, including intermittent, hard-to-reproduce cases. ● Bonus: knowledge base / RAG, dynamic variables, multi-agent transfer, post-call analysis, and the ElevenLabs API/SDK. To apply, please include 1. A short description of a long, multi-node ElevenLabs agent you built: how many nodes, what tools, and what it did. 2. How you'd approach diagnosing duplicate question/answer issues in a 20+ node flow (a quick paragraph, since we want to see how you think). 3. Your availability and rate. Applications that just say "I'm an AI expert" without specific ElevenLabs experience will be skipped. We're looking for someone who has lived in this platform.