Yatin Kumar
Software Engineer
Open to Work
- Target role
- Software Engineer
- Availability
- Actively looking
- Experience
- Beginner
- Working preference
- Hybrid · Gurgaon
pythonc++javaFastAPIDatabricksOpenAI APILangChainSemantic SearchETL PipelinesNumPyCI/CDRAGSQL ServerAzureReactGitHub ActionsDockerREST APIsPydanticAsync Processing
Stock Signal App- LLM-Driven Market Intelligence Pipeline
ViewFastAPI, FinBERT, AsyncIO, NVIDIA NIM
Cut end-to-end inference latency to ~2–4s by parallelizing ingestion with AsyncIO and batching FinBERT sentiment inference.
Quantixiom Chatbot - Production GenAI Integration
ViewReact, TypeScript, NVIDIA NIM, Ollama, OpenAI API
Architected a plug-and-play provider-adapter pattern across OpenAI, NVIDIA NIM, and Ollama, cutting provider-switching integration overhead 70%.
Thera-Mistral - QLoRA Fine-Tuned Conversational LLM
Mistral-7B, QLoRA, PEFT, Unsloth, HuggingFace TRL, FastAPI, CUDA
Fine-tuned Mistral-7B via QLoRA on a CBT-informed dataset, training 41.9M adapter parameters with 4-bit NF4 quantization, reducing VRAM requirements 6