Applied LLM Engineer

Tanishkaa Advisory

Run LoRA/QLoRA with HF stack (transformers, datasets, peft, accelerate, bitsandbytes).

Quantize/export (AWQ, GPTQ, GGUF), stand up inference (vLLM, llama.cpp, TensorRT-LLM)

Build RAG: chunking, embeddings (bge/e5), vector stores (pgvector/Qdrant),

PyTorch + HF ecosystem; hands-on LoRA/QLoRA runs and inference serving.

Quantization know-how (AWQ/GPTQ/GGUF) export formats.

Retrieval & reranking experience; solid Python engineering practices.