AI Software Engineer | LLM Evaluation Specialist | Generative AI | Python | JavaScript
Software Engineer building AI training data and coding challenges. I work at the intersection of software engineering and AI evaluation - writing coding problems, reviewing AI-generated code, and building the datasets that help LLMs get better at reasoning.
- 🛠️ Design and review coding challenges for AI training platforms (Python, JavaScript), using Docker for containerized setups and Git for version control
- 🧠 Evaluate LLM outputs for correctness, bias, and reasoning quality across platforms like Turing and Handshake
- 📊 Build bilingual (Hindi/English) datasets and Chain-of-Thought math reasoning content for LLM fine-tuning
- 🔍 Work daily in Linux/Bash environments
Python JavaScript Bash Docker Git Linux
• AI Agents • LLM Evaluation • Code Generation • Benchmark Creation • Prompt Engineering • Search Quality • NLP • Reinforcement Learning from Human Feedback
Working on AI code evaluation and technical assessment design as a contractor with Handshake, alongside LLM evaluation work with Turing.
- 🚀 AI Coding Challenges – Production-style Python & JavaScript coding challenges with automated testing
- 🤖 LLM Evaluation Toolkit – Rubric-based framework for evaluating AI model responses
- 🐍 Python Automation – Dataset validation and workflow automation tools
- 🐳 Docker Playground – Containerized FastAPI applications and Docker examples
- 🐧 Linux Bash Toolkit – Practical Bash scripts for automation and system utilities
- ✨ Prompt Engineering Lab – Prompt patterns, evaluation templates, and structured prompting examples
- Write clean, testable code
- Prefer reproducible environments
- Build reliable evaluation pipelines
- Document decisions clearly
- Keep learning through hands-on projects