Description

Engineer systems leveraging Large Language Models to solve complex problems.

Responsibilities

• Develop Retrieval Augmented Generation (RAG) pipelines using LLMs.
• Implement prompt engineering, including system/tool prompts, function calling, and versioning via evaluations.
• Establish evaluation and observability frameworks, covering ground truth setup, confusion metrics, LLM-as-judge, and monitoring cost/latency.
• Design and implement retrieval strategies and prompt patterns to manage context and mitigate hallucinations.
• Orchestrate complex workflows using tools like Airflow or Dagster.

Required Skills

• 5+ years of professional experience in software engineering.
• Expertise in Python programming.
• Proficiency with LLM frameworks such as LangChain or LlamaIndex.
• Hands-on experience with cloud LLM providers: Azure OpenAI, AWS Bedrock, or Vertex AI.
• Experience with workflow orchestration tools (Airflow, Dagster).
• Knowledge of security practices, including PII handling and RBAC.
• Demonstrated ability in prompt engineering and model evaluation.

Key Skills

Education

Bachelor's degree