Seeking an LLM Engineer to develop applications and infrastructure using Large Language Models.
Responsibilities:
- Develop LLM-powered applications.
- Integrate foundation models through APIs.
- Implement RAG architectures.
- Develop prompt engineering and optimization strategies.
- Implement model evaluation and testing.
- Fine-tune models when appropriate.
- Build vector search and embedding pipelines.
- Develop LLM APIs and production services.
- Monitor model performance, cost, and latency.
Required Skills:
- LLMs.
- Python.
- OpenAI/Azure OpenAI/Anthropic/Gemini.
- Transformers.
- Hugging Face.
- RAG.
- Embeddings.
- Vector databases.
- LangChain/LlamaIndex.
- REST APIs.