LLM Engineer

Location- Remote- Anywhere in united states.

US Citizen or Green card - W2 only.

Company Introduction- We are a forward-thinking organization seeking a proficient LLM Engineer, emphasizing a "Builder-Architect" mindset to enhance our AI application development.

Responsibilities- Architectural Design: Develop comprehensive architectures for LLM applications, encompassing data ingestion and orchestration.

• RAG Development: Create tailored RAG solutions, focusing on accuracy, latency, and relevance through advanced techniques.

• Full Life Cycle Implementation: Assume responsibility for the entire development process, from research to production deployment.

• Deployment & Ops: Utilize Docker and Kubernetes for application containerization and establish robust CI/CD pipelines.

• Evaluation & Monitoring: Set up frameworks to assess LLM performance and monitor for issues such as hallucinations.

• Infrastructure: Choose and manage Vector Databases, integrating them into scalable cloud environments.

Requirements- Experience: Minimum of 5 years in Machine Learning or Software Engineering, with 2+ years focused on LLMs.

• The "Architect" Mindset: Proven capability to create architectural diagrams and substantiate technical decisions.

• RAG Mastery: Demonstrated expertise in constructing RAG systems from inception, beyond high-level wrappers.

• Tech Stack: Proficient in advanced Python, LangChain/LlamaIndex, PyTorch/TensorFlow, and FastAPI.

• DevOps: Practical experience with Docker, Kubernetes, and cloud-native deployment methodologies.

• Data Engineering: Strong SQL proficiency and experience managing large-scale unstructured datasets.