Description

You will design, build, and integrate applications using Large Language Models, managing context, retrieval, and evaluation pipelines. This role requires strong systems design skills to make practical tradeoffs while implementing MLOps patterns and model integration strategies.

This role is on-site.

Responsibilities

• Build and integrate applications with LLMs using Python and secondary languages like Java, Swift, Ruby, or JavaScript.
• Implement structured retrieval approaches using vector or graph databases to manage context effectively.
• Design and execute LLM evaluation pipelines that combine quantitative and qualitative methods to align metrics with user workflows.
• Translate technical findings into clear guidance for other engineers, explaining AI engineering practices and MLOps patterns.
• Perform systems design tradeoffs and deliver production-ready applications with a focus on reliability and performance.

Required Skills

• 5+ years of hands-on programming experience with Python required.
• Proficiency in at least one additional language: Java, Swift, Ruby, or JavaScript.
• Experience building and integrating applications with LLMs and understanding retrieval-augmented generation (RAG) principles.
• Practical knowledge of vector databases, graph databases, or other structured retrieval approaches.
• Familiarity with MLOps patterns, including evaluation methods and context management strategies.
• Ability to explain complex AI engineering concepts to peers and stakeholders clearly.

Preferred Skills

• Experience with Hugging Face ecosystem (Transformers, Datasets) and PyTorch for fine-tuning or lightweight model training.
• Implementation experience with LangChain and Model Context Protocol (MCP).

Key Skills

Education

Any Graduate