Refactoring and architectural redesign of the existing Django/Python application

Project: YOKA ASSIST — intelligent diagnostic and training system for mining equipment Project Description It is required to develop the YOKA ASSIST intelligent system based on a Telegram bot using artificial intelligence. The main task of the project is to create a digital assistant for electricians, mechanics, operators, and engineering and technical personnel, which will assist in diagnosing faults, training employees, and storing a technical knowledge base. The first stage of the project is focused on mining equipment (EKG excavators, SBSh drilling rigs, and other equipment), but the architecture should be universal and easily scalable. Main Functionality Telegram Bot - Modern interface. - Menu with buttons. - User authorization. - Access rights separation (user, administrator, chief administrator). Artificial Intelligence Knowledge Base A knowledge storage system needs to be created. Support: - PDF; - Word; - Excel; - photographs; - diagrams; - videos; - instructions; - equipment passports; - technical documents. After information is added by the administrator, the AI should use it in responses without changing the program code. Equipment Diagnostics Search support: - by error code; - by protection name; - by cabinet; - by unit; - by equipment; - by symptoms. For each fault, it is desirable to provide: - description; - possible causes; - sequence of checks; - photographs; - diagrams; - video materials; - links to related documents. Dynamic Buttons Buttons should be generated automatically depending on the situation. For example: - Check cabinet. - View diagram. - View video. - Next stage of diagnostics. - Go back. Administrative Panel The chief administrator should be able to: - add equipment; - create new errors; - add documents; - upload photographs; - upload videos; - edit the knowledge base; - manage users; - assign administrators of individual departments. QR System Each cabinet, unit, or equipment can have its own QR code. After scanning, the user immediately enters the corresponding section of the Telegram bot. Repair Log A log of completed work needs to be implemented. Functions: - who performed the repair; - date and time; - equipment; - description of completed work; - materials used; - comments; - repair history. Analytics It is desirable to implement: - most common faults; - repair statistics; - time to resolve faults; - reports on equipment; - reports on employees. Scalability The architecture should allow for adding new types of equipment, new enterprises, new departments, and new knowledge bases without rewriting the project. Technologies Desirable: - Python; - Telegram Bot API; - PostgreSQL or SQLite (SQLite is allowed in the first stage); - integration with AI via API; - modular architecture; - possibility of further connecting a web panel. What is expected from the contractor - Development of a fully functional project. - Clean and understandable code. - Documented project structure. - Possibility of further development without complete redesign. - Assistance with initial deployment and setup of the project. The project is long-term. After successful completion of the first stage, further improvements and development of the system are possible.

I'm looking for an experienced Python developer who can conduct a full audit of the existing project, fix errors, and bring it to fully stable operation. If necessary, a complete redesign of the project architecture or writing a new implementation while preserving all necessary functionality is allowed. What I will provide The source code of the current bot. A video demonstrating how the bot should work. A complete technical specification with the logic of operation. Main task The goal is to restore the stable operation of the bot and ensure the execution of the full scenario without failures. If the current architecture cannot be effectively fixed, a complete redesign of the project is allowed. The main objective is not to preserve the existing code but to obtain a fully functional, stable, and maintainable product. What needs to be done 1. Conduct a project audit Before starting work, it is necessary to: study the existing code; identify the reasons why the bot stopped working; assess what can be fixed and what is more reasonable to rewrite. 2. Restore all functionality After the work is completed, the bot should correctly execute the entire scenario: registration of a new account; confirmation of login via code from email; authorization; execution of the scenario according to the technical specification; completion of work; transition to the next account. All stages must work automatically without manual intervention. 3. Fix existing errors It is necessary to eliminate any errors related to: authorization; receiving the confirmation code; unstable operation; freezing; unexpected program termination; errors after website updates; incorrect exception handling. 4. Make the project resilient The bot must: correctly handle errors; not enter infinite loops; automatically terminate unsuccessful scenarios; correctly continue operation after non-critical errors; maintain clear logs. 5. Control panel It is necessary to preserve or redesign the control panel. It should allow: to start and stop operation; to change necessary settings; to view the current status; to view the log of operations and errors. The interface should be clear and stable. 6. Code Code requirements: clear project structure; separation of logic into modules; possibility of further support. 7. Compatibility The project must run on a modern version of Python. The contractor must provide a complete list of dependencies and instructions for running. 8. Result verification Before handing over the project, the contractor must demonstrate a fully working scenario on video: project launch; completion of the full cycle; absence of errors; correct operation of all functions. What to provide after completion source code; all modified files; instructions for running; list of dependencies; video demonstration of operation; brief description of the changes made. Important The work is considered completed only after all functionality described in the technical specification and demonstration video works stably without critical errors. If during the audit it turns out that the current project cannot be effectively fixed, a complete redesign is allowed while preserving all necessary functionality. When responding, please indicate immediately: experience with Python; experience in browser automation (Playwright, Selenium, or similar tools); experience with REST API; cost of work; estimated completion time.

We are looking for a highly skilled AI application engineer and full-stack backend developer to build a production-ready AI-powered document validation, refinement, and approval workflow. This is not a simple prompt engineering role. We need someone who can design and implement a real AI application with strong backend architecture, Claude API integration, structured validation logic, audit trails, secure data handling, and human-in-the-loop review workflows. The system will act as an intelligent quality assurance layer for submitted reports and documents. It should review completed submissions, identify issues, improve content quality, apply business rules, protect sensitive information, and either approve the document automatically or route it for human review. The developer will be responsible for building a workflow that can: Pull completed documents, reports, or submissions from an external platform via API Analyze the full document, including structured answers, ratings, selections, narratives, comments, and free-text fields Perform semantic audits to detect logical conflicts, contradictions, missing information, vague statements, unsupported claims, or incomplete sections Validate that structured responses and written content are consistent with each other Apply custom validation rules, editorial guidelines, formatting standards, tone requirements, and business logic Detect, tokenize, mask, or securely handle PII, confidential data, and sensitive security-related information before AI processing where required Rewrite and enhance narratives, comments, and document sections for grammar, clarity, professionalism, consistency, and readability Preserve the original meaning, observations, and intent while improving the final output Standardize writing style across documents without making every report sound generic or over-normalized Flag content that appears inconsistent, fabricated, vague, incomplete, sensitive, or requiring human review Generate specific validation notes explaining why a document failed review and what needs to be corrected Automatically generate clarification or revision requests when more information is needed Support approval workflows where documents are: Automatically approved when confidence thresholds are met Routed to a human editor or validator for review Returned to the original submitter for revision or clarification Maintain a complete audit trail showing: Original submission Tokenized or masked sensitive data events AI findings and recommendations AI-rewritten content Human edits Approval or rejection decisions Final approved version Write approved and validated content back to the source platform through API integration The role also requires building an editor and final-decision workflow. Human reviewers should be able to inspect the AI’s findings, compare original and revised content, make edits, approve changes, reject recommendations, and finalize the document before it is sent downstream. Ideal experience includes: Strong Claude API / Anthropic API integration experience Experience building AI-powered document review, validation, editing, or compliance workflows Strong backend architecture skills Full-stack development ability Experience with API integrations, webhooks, queues, job processing, and database design Ability to design structured AI outputs, confidence scoring, rule-based validation, and human-in-the-loop review Experience with PII detection, tokenization, masking, encryption, access control, and secure AI data handling Experience building secure audit trails and approval systems Strong understanding of prompt design, but also the engineering skills to turn prompts into a reliable production system We are looking for someone who has already built serious AI applications, not someone who only writes prompts. The right person should be able to design the architecture, integrate with external APIs, manage document processing logic, protect sensitive data, build the review interface, and deliver a reliable workflow that can be used in production.

We are looking for a 3D GenAI Engineer / AI 3D Pipeline Developer It is necessary to create a solution that can qualitatively generate 3D models from a single image or multiple images. It is important that this is not just a ready-made demo, but a clear and reproducible process: from the input image to a full-fledged 3D asset with mesh, geometry, textures, and the possibility of further use. What needs to be done: - test modern image-to-3D models and approaches; - determine which option is best suited for our task; - use Trellis, Hunyuan3D, or similar solutions; - if necessary, use Gaussian Splatting in the 3D pipeline; - configure the conversion of Gaussian Splat / splat representation into 3D mesh; - obtain usable geometry; - generate high-quality textures; - bring the result to a usable 3D asset state; - find the optimal balance between quality, generation speed, and pipeline complexity; - build a clear process that can be repeated for different images; - perform fine-tuning, LoRA, or other model adaptations for specific types of objects.

It is necessary to connect the application form on the landing page to keycrm. I will provide all necessary access. Please write how much time and cost this task will take.