Hugging Face Launches Job Searcher Tool to Enhance AI Recruitment

Hugging Face outlined updates on Job Searcher: job Searcher

You click “Easy Apply” until your eyes hurt. You write the same cover letter forty times. By month two of a search, you’re applying to roles you wouldn’t take, in industries you don’t care about, because at that point the cost of thinking about each listing is higher than the cost of submitting to one. Watch the short tour: drop a resume, watch the queries stream, read the per-job reasoning. What you get back isn’t a list of fifty roles. It’s a small shortlist with defensible reasoning. You can read why the model thinks the second-ranked job beats the third. The teacher is DeepSeek V4 Pro. Strong at structured reasoning, willing to follow a strict output schema, cheap enough to run once over a large corpus offline. It is used as a label generator, not as an inference-time dependency. The student is Qwen3-8B. Small enough to fit on a single ZeroGPU slice once quantized to Q4_K_M, large enough to absorb the teacher’s structured judgement. The corpus came from a closed loop, resume-aware end-to-end: Everything ships in four foreign-key-clean configs at build-small-hackathon/job-search-distill. Two LoRA SFT runs on a single A100 via Modal, one per task: LoraConfig( r=16, lora_alpha=16, task_type=”CAUSAL_LM”, target_modules=[ “q_proj”, “k_proj”, “v_proj”, “o_proj”, “gate_proj”, “up_proj”, “down_proj”, ], ) The Space – Inference (llama.cpp) The Space runs llama-cpp-python with the pre-built CUDA wheel on a HuggingFace ZeroGPU Space. Two design choices that matter: Streaming uses the OpenAI-shaped create_chat_completion(stream=True) so the reasoning lands in the UI token by token.