Job purpose:
Design, evaluate, and refine prompts to guide LLMs in producing accurate, relevant, and high-quality outputs for real-world applications such as voice bots, chatbots, and automation flows.
Who You Are:
- Minimum of 1-2 years of experience working with or around Large Language Models or similar Generative AI technologies.
- Hands-on experience working with LLMs using OpenAI, Hugging Face, or similar platforms.
- Basic understanding of Python and ability to write prompt-related scripts.
- Familiarity with prompt evaluation frameworks and performance metrics.
Key Responsibilities:
- Design and engineer effective prompts for use with LLMs (e.g., GPT, Claude, Mistral).
- Analyze model behavior and refine prompts for accuracy, relevance, and efficiency.
- Collaborate with product, engineering, and ML teams to integrate prompt logic into production systems.
- Conduct testing and evaluation of prompts across multiple tasks and domains.
- Research and experiment with techniques such as few-shot, zero-shot, and chain-of-thought prompting.
What will excite us:
- Experience using LangChain or other LLM orchestration tools.
- Understanding of embeddings, vector databases, and semantic search.
- Prior experience building chatbot or GenAI applications.
- Awareness of model behavior limitations, hallucination risks, and mitigation strategies.
What will excite you:
- In-office opportunity in Ahmedabad with a collaborative and AI-focused team.
- Work on innovative Gen AI projects with real-world impact.
- Exposure to production-level LLM deployment and prompt optimization at scale.
Location: Ahmedabad