Largeton Group
Job Summary
Develop and enhance a Knowledge Assistant for the Pro & Services organization focused on natural language understanding and agentic workflows. Core Responsibilities
Build, evaluate, and iterate on LLM-powered agents for task execution, reasoning, and data retrieval (structured and unstructured). Collaborate with product managers, engineers, and data scientists to integrate AI solutions into customer and associate-facing platforms. Design and own model evaluation and validation pipelines for LLM and RAG workflows, including performance tracking and ablation studies. Write clean, production-grade Python code and reusable ML/AI components. Apply analytical problem-solving to identify patterns, define rules, and optimize agent behavior. Required Qualifications
PhD-level research or applied experience with LLMs and AI. Deep expertise in LLMs, including prompt engineering, fine-tuning, or agentic architectures (e.g., LangGraph, AutoGen, CrewAI). Strong software engineering background; extensive hands-on Python programming skills. Experience with LangChain and/or LangGraph. Hands‑on model evaluation expertise for LLM-based systems, including metric design and A/B or offline testing. Additional / Preferred Skills
Experience with agentic or applied AI projects. Familiarity with tools like CrewAI, AutoGen, Hugging Face Transformers, vector DBs (FAISS, Weaviate, Pinecone). Proficiency with Git, VS Code, and cloud platforms (GCP preferred). Experience with retrieval‑augmented generation (RAG), knowledge graphs, and custom evaluation pipelines. Retail or digital domain experience. Familiarity with evaluation frameworks (TruLens, Ragas, Promptfoo, ReAct‑style). Experience implementing guardrails for LLM safety, compliance, and brand alignment. Disqualifiers
Only generic ML experience without LLM or advanced AI work. Heavy use of low‑code/no‑code ML platforms without software engineering depth. Lack of end‑to‑end hands‑on involvement in model deployment or evaluation. Key Traits
Self‑starter, curious, able to navigate ambiguity, and thrive in a fast‑moving, high‑impact AI innovation team. Strong communication skills to articulate technical LLM/AI experience. Seniority Level
Mid‑Senior level Employment Type
Contract Job Function
Engineering and Information Technology Industries
IT Services and IT Consulting
#J-18808-Ljbffr
Develop and enhance a Knowledge Assistant for the Pro & Services organization focused on natural language understanding and agentic workflows. Core Responsibilities
Build, evaluate, and iterate on LLM-powered agents for task execution, reasoning, and data retrieval (structured and unstructured). Collaborate with product managers, engineers, and data scientists to integrate AI solutions into customer and associate-facing platforms. Design and own model evaluation and validation pipelines for LLM and RAG workflows, including performance tracking and ablation studies. Write clean, production-grade Python code and reusable ML/AI components. Apply analytical problem-solving to identify patterns, define rules, and optimize agent behavior. Required Qualifications
PhD-level research or applied experience with LLMs and AI. Deep expertise in LLMs, including prompt engineering, fine-tuning, or agentic architectures (e.g., LangGraph, AutoGen, CrewAI). Strong software engineering background; extensive hands-on Python programming skills. Experience with LangChain and/or LangGraph. Hands‑on model evaluation expertise for LLM-based systems, including metric design and A/B or offline testing. Additional / Preferred Skills
Experience with agentic or applied AI projects. Familiarity with tools like CrewAI, AutoGen, Hugging Face Transformers, vector DBs (FAISS, Weaviate, Pinecone). Proficiency with Git, VS Code, and cloud platforms (GCP preferred). Experience with retrieval‑augmented generation (RAG), knowledge graphs, and custom evaluation pipelines. Retail or digital domain experience. Familiarity with evaluation frameworks (TruLens, Ragas, Promptfoo, ReAct‑style). Experience implementing guardrails for LLM safety, compliance, and brand alignment. Disqualifiers
Only generic ML experience without LLM or advanced AI work. Heavy use of low‑code/no‑code ML platforms without software engineering depth. Lack of end‑to‑end hands‑on involvement in model deployment or evaluation. Key Traits
Self‑starter, curious, able to navigate ambiguity, and thrive in a fast‑moving, high‑impact AI innovation team. Strong communication skills to articulate technical LLM/AI experience. Seniority Level
Mid‑Senior level Employment Type
Contract Job Function
Engineering and Information Technology Industries
IT Services and IT Consulting
#J-18808-Ljbffr