About

We are looking for an LLM Developer for a short 2–3 day project involving model tuning and dataset preparation. The ideal candidate can work fast, experiment quickly, and deliver optimized results. Responsibilities Tune and optimize GPT models (prompts, parameters, guardrails). Build small scraping pipelines (Python: Scrapy, BeautifulSoup, Playwright/Selenium). Clean and prepare scraped data for training/fine-tuning. Set up basic RAG components (embeddings + vector DB like Pinecone/Qdrant/FAISS). Integrate tuned model through simple backend API. Run quick evaluations for accuracy, hallucinations, and consistency. Requirements Strong Python experience (scraping + automation). Hands-on experience with GPT model tuning or fine-tuning (OpenAI, LoRA/QLoRA). Familiarity with embeddings, vector databases, and basic RAG workflows. Ability to deliver fast, clean prototypes. Nice to Have Experience with vLLM, LangChain, LlamaIndex. Knowledge of cloud deployment (AWS/GCP) and Docker. Why This Gig? Super short, high-impact project. Work directly on core LLM optimisation + data pipeline tasks. Potential for long-term collaboration after successful delivery.