We’re looking for a highly skilled and motivated developer with a strong background in Large Language Model (LLM) application development and production-grade system engineering. This is an exciting opportunity to work on cutting-edge AI technologies and help us build scalable, intelligent applications that deliver real value to users. Key Responsibilities: Design, develop, and maintain applications leveraging LLMs (e.g., OpenAI GPT, Claude, or open-source models like LLaMA, Mistral, etc.). Build robust, scalable, and maintainable backend systems ready for production deployment. Design and implement feature flagging strategies to enable controlled roll-outs of new app features. Plan and execute A/B testing and experimentation to optimize user experiences and improve system performance. Collaborate with cross-functional teams including product managers, data scientists, and designers to build innovative solutions. Monitor, debug, and optimize system performance in a cloud-based environment. Maintain high code quality through automated tests, code reviews, and documentation. Required Skills & Experience: Proven experience developing applications using LLMs either via APIs (OpenAI, Anthropic, Cohere) or open-source models. Deep understanding of prompt engineering, retrieval-augmented generation (RAG), and fine-tuning LLMs (nice to have). Strong experience in backend development using Python, Node.js, or similar languages. Solid working knowledge of cloud infrastructure and deployment processes (AWS, GCP, or Azure). Hands-on experience with feature flagging tools (e.g., LaunchDarkly, Flagsmith, or internal frameworks). Extensive experience designing and running A/B tests and experiment frameworks. Excellent problem-solving skills, system design capabilities, and debugging techniques for large-scale applications. Strong communication skills and ability to work independently in a remote team environment. Nice to Have: Experience working on AI-powered products at scale. Exposure to data analytics, metrics tracking, and product experimentation pipelines. Familiarity with ML Ops tools such as MLflow, Weights & Biases, or similar. Project Details: Project type: Ongoing / Long-term (with potential for full-time engagement) Commitment: Part-time to Full-time, depending on availability and fit Location: Remote Compensation: Competitive, based on experience To Apply: Include a brief summary of your relevant experience and why you’re excited about this project. Share your portfolio, GitHub profile, or links to relevant past work. Highlight specific projects involving LLMs, experimentation, or production-grade system architecture.