Responsibilities: Key Responsibilities
- Develop and implement Generative AI solutions using LLMs (e.g., GPT, open-source models)
- Work on prompt engineering to improve model outputs and accuracy
- Build simple AI-powered applications (chatbots, assistants, automation tools)
- Integrate AI models using APIs (OpenAI, Azure OpenAI, Hugging Face, etc.)
- Preprocess and manage text and unstructured data
- Assist in building end-to-end pipelines for GenAI applications
- Evaluate and monitor model performance (accuracy, latency, cost)
- Collaborate with data engineers and software developers on AI use cases
- Stay up to date with latest advancements in AI and LLM ecosystems
Required Skills
- Strong programming skills in Python
- Basic understanding of Machine Learning and NLP concepts
- Familiarity with Generative AI / LLMs (theoretical or project-based)
- Knowledge of REST APIs and JSON
- Understanding of data structures and problem-solving
- Ability to write clean, modular, and scalable code
