Responsibilities of the Candidate:
- Develop applications using LLM APIs (Azure / OpenAI) and open-source models.
- Implement prompt templates, evaluation loops and model instruction tuning.
- Design and develop machine learning algorithms and deep learning applications
- Build RAG pipelines: ingestion → embeddings → vector DB → retrieval.
- Ship prototypes (FastAPI endpoints, simple UIs) and production grade deployments.
- Write unit tests, monitoring hooks and participate in cost-control for API usage.
- 1–3 yrs experience with Python/Keras/PyTorch.
- Practical experience with Hugging Face / transformers or calling hosted LLM APIs.
- Familiarity with embeddings + any vector DB (Pinecone / Weaviate / Milvus).
- Basic web/API skills (FastAPI/Flask).
- Azure/AWS/GCP hands-on experience
- with ML background experience
Requirements:
- LangChain experience, Azure/Azure OpenAI exposure, experience with prompt engineering frameworks.
- Basic knowledge of authentication (Azure AD / OAuth), SQL, and basic infra (Docker/Kubernetes).
