Description

You will design and iterate on LLM-powered agents to integrate into enterprise systems.

This role is hybrid.

Responsibilities

• Design and iterate on LLM-powered agents using internal frameworks.
• Build prompts and context strategies for data summarization, workflow automation, and image-text comparison.
• Run structured, reproducible experiments tracking versions, prompt variants, latency, and failure cases.
• Collaborate with engineers and product managers to integrate agents into Epicor systems.
• Design telemetry to monitor agent performance, usage trends, and error patterns.

Required Skills

• 4+ years in data science or applied ML roles.
• 1+ year developing real applications using LLMs.
• Strong grasp of prompt engineering patterns, task decomposition, and few-shot strategies.
• Familiarity with managing long contexts, chunking, summarization, and retrieval (RAG).
• Proven experience in tracking experiments, evaluation design, metric creation, and telemetry.
• Proficiency in Python and Git.
• Excellent written and verbal communication skills.
• Familiarity with ERP concepts.

Preferred Skills

• Exposure to .NET/C# environments and lightweight deployment workflows (containers, APIs, CI/CD).

Key Skills

Education

Any Graduate