We are seeking a versatile and passionate **AI **to join our data science and engineering team. You will be instrumental in bridging the gap between data science research and production-ready applications, building scalable machine learning systems that drive business value. This role requires a strong balance of software engineering principles and ML expertise.
Key Responsibilities
-
Design, develop, and deploy end-to-end AI pipelines, focusing on integrating Large Language Models (LLMs) and Foundation Models into production environments.
-
Work closely with stakeholders to transition AI prototypes and experimental agents into scalable, production-grade systems, implementing modern LLM Ops practices.
-
Develop robust, efficient code using Python and frameworks such as LangChain, LlamaIndex, or AutoGPT, alongside traditional libraries like PyTorch or TensorFlow when needed.
-
Implement advanced monitoring for AI applications, focusing on output quality, hallucination detection, and performance tracking (e.g., using RAGas or Arize Phoenix).
-
Collaborate with Data Engineers to build efficient data pipelines for vector databases (Chroma, Pinecone, Weaviate) and optimize context retrieval for RAG.
-
Stay at the forefront of the rapidly evolving Generative AI landscape, exploring new techniques in prompt engineering, fine-tuning, and agentic workflows.