We are looking for a Senior Mid Full-Stack Developer (Python First) to lead the development of AI-driven automation pipelines and browser-based workflows. This role is hands-on, highly autonomous, and ideal for someone who thrives in under-documented environments and enjoys turning complex, unstructured inputs (audio, PDFs, images) into reliable, structured outputs. He will work closely with the Lead Developer and CTO-level leadership, contributing directly to architectural decisions and long-term platform scalability.

Key Responsibilities:

Core Development & Automation

• Lead backend and automation development using Python as the primary language
• Design and implement AI-powered pipelines for processing transcripts, PDFs, images, and scanned documents
• Integrate OpenAI models for structured data extraction and workflow automation
• Implement Whisper API for speech-to-text processing
• Build and maintain OCR pipelines using third-party OCR solutions (e.g., Google OCR)
• Generate consistent, structured JSON outputs to ensure reliable AI responses

Browser Automation & Extensions

• Build and maintain a Chrome browser extension using:
• Playwright (Python – preferred), or
• Puppeteer (JavaScript – acceptable)
• Develop browser automation workflows to support document handling and form completion
• Prototype and iterate on automated flows, including auto-filled PDF generation

Front-End & Integration Support

• Contribute to front-end development where needed (JavaScript; React / Next.js exposure is a plus)
• Document integrations and automation logic to ensure scalability and maintainability
• Solve technical challenges involving emerging tools and limited documentation

Experience and Qualifications:

Education:

• Bachelor’s degree in Computer Science, Software Engineering, or a related field preferred but not required
• Equivalent professional experience is highly valued

Technical Experience

• 5+ years of hands-on software development experience, with strong depth in Python
• Proven experience building automation pipelines that process unstructured data (audio, PDFs, images, scanned documents)
• Hands-on experience integrating OpenAI APIs for structured data extraction and workflow automation
• Experience using Whisper API or similar speech-to-text technologies
• Practical experience implementing or consuming OCR APIs (e.g., Google OCR or equivalent)
• Experience designing and enforcing structured JSON outputs for consistent AI responses
• Experience with browser automation using Playwright (preferred) or Puppeteer
• Working experience with JavaScript (Node.js exposure; React / Next.js experience is a plus)
• Prior experience building Chrome browser extensions is a strong advantage

Work Style & Problem-Solving

• Demonstrated ability to work independently in early-stage or fast-moving environments
• Experience operating within underdocumented or evolving systems
• Track record of taking projects from concept to working prototype with minimal guidance
• Comfortable making architectural decisions and trade-offs in ambiguous situations

Technical Qualifications

• Strong proficiency in Python as a primary development language
• Solid understanding of AI model integration, prompt design, and output reliability
• Working knowledge of speech-to-text, OCR, and document automation workflows
• Familiarity with browser automation frameworks and extension architecture
• Competence in JavaScript fundamentals (advanced front-end specialization not required)

Professional & Personal Qualifications

• Strong analytical and problem-solving skills
• High ownership mindset with the ability to self-direct work
• Adaptable, curious, and comfortable learning emerging tools with limited documentation
• Interest in building long-term, scalable platforms, not just short-term features
• Clear communicator, especially when documenting technical decisions and integrations