Description

You will design, build, and deploy practical AI-powered applications, focusing on LLM integration and system reliability.

This role is on-site.

Responsibilities

• Design and deliver AI applications, making informed systems design tradeoffs.
• Build and integrate applications utilizing Large Language Models (LLMs) and structured retrieval approaches.
• Apply AI engineering practices including retrieval, context management, and evaluation methods.
• Translate complex technical AI findings into clear guidance for engineering teams.
• Design and execute experiments with defined hypotheses and baselines.

Required Skills

• 5+ years of professional software engineering experience.
• Proficiency in Python.
• Experience with LLMs and vector/graph databases for retrieval.
• Hands-on programming in at least one of: Swift, Ruby, or JavaScript.
• Experience with MLOps patterns.
• Experience with PyTorch for model training and evaluation.
• Practical experience with frameworks like LangChain.

Preferred Skills

• Familiarity with the Hugging Face ecosystem (Transformers, Datasets).
• Experience designing LLM evaluation pipelines balancing quantitative and qualitative metrics.

Key Skills

Education

Any Gradute