Description

You will design and build production-grade LLM systems, including agentic workflows, RAG pipelines, and deterministic orchestration.

This role is hybrid.

Responsibilities

• Develop agentic workflows with multi-step reasoning, tool use, and agent-to-agent communication.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines and context engineering strategies.
• Create ground-truth datasets and implement LLM-as-judge and rule-based evaluation methods.
• Convert prototypes into reliable, production-grade services using Python and structured-output validation.
• Integrate systems with Kubernetes, Azure, and AWS, managing CI/CD pipelines and observability.

Required Skills

• 5+ years of experience with LLM systems, including agentic workflows and RAG.
• Strong Python skills, including packaging, testing, and structured-output validation.
• Deep understanding of transformers, neural networks, and applied statistics.
• Experience with Kubernetes and cloud platforms (Azure and/or AWS, including Bedrock/SageMaker).
• Proficiency in CI/CD pipelines and observability tools (cost, latency, caching).
• Ability to create evaluation suites and separate signal from prompt noise.
• Bachelor’s degree in Computer Science or related field.

Preferred Skills

• Experience with managed LLM platforms like Azure OpenAI or AWS Bedrock.
• Background in training, fine-tuning, or distilling models.
• Familiarity with enterprise AI governance and regulated environments.

Key Skills

Education

Bachelor's degree