About the role
Responsibilities:
- Design and develop scalable LLM-based applications using Python.
- Build and optimise RAG (Retrieval-Augmented Generation) pipelines.
- Develop multi-agent systems and orchestration workflows.
- Integrate LLMs with APIs, databases, and enterprise systems.
- Work with vector databases (e. g., FAISS, Pinecone, Chroma).
- Implement prompt engineering, evaluation, and optimisation techniques.
- Collaborate with business teams to assist in translating business problems into AI solutions.
- Continuously experiment with new models, frameworks, and architectures.
Requirements:
- 2-3 years of hands-on experience in Python development.
- Strong understanding of data structures, algorithms, and system design fundamentals.
- Experience or exposure to LLMs / Generative AI frameworks (LangChain, LlamaIndex, etc. )
- Familiarity with REST APIs, backend systems, and integrations.
- Basic understanding of machine learning concepts.
- Experience with Git, Docker, and modern development workflows.
- Bachelor's or Master's degree in Computer Science or a related field.