Description

You will design, build, and deliver applications powered by large language models, focusing on system design tradeoffs and practical engineering.

This role is on-site.

Responsibilities

• Build and integrate applications with LLMs using vector, graph, or structured retrieval approaches.
• Design and execute experiments with clear hypotheses, baselines, and success criteria.
• Implement LLM evaluation pipelines combining quantitative and qualitative methods to align metrics with user workflows.
• Apply AI engineering practices including context management, evaluation, and MLOps patterns.
• Explain and apply AI engineering practices to other engineers, translating technical findings into clear guidance.

Required Skills

• 5+ years of experience in applied data science or software engineering.
• Hands-on programming in Python, plus one or more of Swift, Ruby, or JavaScript.
• Experience building applications with LLMs.
• Familiarity with vector databases, graph databases, or structured retrieval.
• Understanding of MLOps patterns, retrieval, and context management.
• Strong communication skills for technical guidance.

Preferred Skills

• Experience with Hugging Face ecosystem (Transformers, Datasets, evaluation libraries).
• Experience with PyTorch for fine-tuning, evaluation, and lightweight model training.
• Experience implementing model integration approaches such as LangChain and MCP.

Key Skills

Education

Any Graduate