Nepali/Ukranian AI Automation Engineer Full Time

@Hubready

Hello!, I am a US-based senior software engineer, and I’d be a strong fit for this role because the real challenge here is not just building AI, it’s understanding an existing system quickly, mapping how it behaves, then extending it without breaking what already works. I’m used to inheriting codebases, tracing workflows, documenting logic, and turning messy systems into reliable automation. My approach is practical: 1. Audit the current system and identify hidden dependencies 2. Recreate the behavior in a clear flow map 3. Extend and harden the AI automation layer 4. Test, document, and leave you with something clean and supportable That’s usually where projects like this succeed or fail, and I pay attention to those details. Relevant work examples: - AI workflow automation platform for an operations team - Internal LLM assistant for knowledge lookup and task routing - Python-based data extraction and enrichment pipeline - SaaS automation layer with API integrations and monitoring Could you please clarify the following questions to help me better understand the project? 1. What parts of the current system are already working, and what specifically needs to be extended? 2. Is there existing documentation, or should I begin with codebase/system behavior discovery? 3. What is the expected handoff at the end: code only, documentation, deployment support, or all three? If helpful, I can start by stabilizing the inherited system first, then move into the new automation

@cliftonc20

Hi, Your system’s focus on extending and maintaining production AI-driven ad generation workflows aligns with my experience building and scaling AI platforms with complex backend and frontend integrations. The main technical risk is maintaining system stability while incrementally extending features in a live environment that integrates multiple AI APIs and cost tracking. I typically design systems with clear separation between ingestion, orchestration, and response layers to isolate changes and facilitate testing. This approach reduces risk when working with inherited codebases and complex AI API interactions. I also emphasize reliability measures such as robust error handling, retry logic, and monitoring to minimize disruptions and maintain cost visibility. I can start by reviewing your current ingestion and orchestration architecture to identify potential fragilities and outline improvements for safe feature extension. Thanks, Clifton

@diektech

Hi — Elias here from Miami. I understand you're looking to inherit and extend an existing AI automation system. The goal is to ensure it functions seamlessly while preparing it for future enhancements. What usually matters most here is maintainability and scalability. A common issue in systems like this is the complexity of the existing codebase, which can make it challenging to identify potential pitfalls. The tricky part is usually understanding the current data flows and integration points to ensure new features align with the existing architecture. My approach would involve a thorough assessment of the current system, mapping out its architecture, and identifying areas for improvement. I would focus on building a modular structure to ease future updates and integrations, enhancing reliability and supporting your long-term goals. I have experience with similar AI integration projects, improving automation capabilities while ensuring a solid foundation for future features. A few questions to better understand the scope: Q1 – What specific functionalities need immediate attention or enhancement? Q2 – Are there existing integrations that are critical to maintain during the extension process? Q3 – What are your expectations regarding the system's scalability as you plan for future growth? Happy to discuss the details and suggest the best technical approach. Looking forward to hearing from you.