Applied AI Engineer

Design, implement, and optimize Generative AI applications using Python and frameworks such as FastAPI. 

Build AI solutions using LLM frameworks like LlamaIndex and LangChain. 

Implement containerized deployments using Docker. 

Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for improved information retrieval. 

Work with self-hosted and cloud-based vector databases for efficient search and retrieval. 

Design and manage knowledge graphs and graph-based RAG systems. 

Implement re-ranking models and retrieval optimization techniques. 

Apply prompt engineering and context engineering to enhance model performance. 

Establish guardrails to ensure safe, ethical, and compliant AI deployments. 

Build data preprocessing and transformation pipelines for structured and unstructured data. 

Perform inference using offline LLMs via platforms like Ollama or Hugging Face (Llama, Mistral). 

Integrate online LLM providers such as OpenAI, Anthropic, or GCP for real-time inference. 

Monitor AI workflows using observability tools like MLflow or Arize Phoenix. 

Evaluate model performance using frameworks such as TruLens or custom-built evaluation systems. 

Continuously improve AI systems based on evaluation insights, metrics, and user feedback.