Applied LLM Engineer
Core
Build and maintain an AI concierge (YOlanda) that answers user questions and executes account actions within five responses, managing handoffs to specialist models and ensuring cost-effective, accurate production operations.
Role type
Senior Applied LLM Engineer (Production & Optimization)
Builds
An AI concierge interface for a connectivity platform, handling plan changes, top-ups, and balance queries via LangChain/LangGraph.
Domain
Telecom/Connectivity industry + Large Language Models (LLMs) and RAG
Deliverable
production ML models
Required skills
Python, LangChain, LangGraph, Prompt Engineering, LLM Evaluation, Production Operations (Tracing/SLOs), Semantic Caching, Cost Optimization, Governance/Security Controls, Retrieval Augmented Generation (RAG)
Preferred skills
Experience with frontier and open-source models, Red Teaming, CI/CD release gates for AI
Technologies
LangChain, LangGraph, Python, Git, JSON, Regex, Markdown
Responsibilities
Design system prompts and evaluation sets; manage context and handoff boundaries; implement caching and routing logic; monitor cost, latency, and SLOs; enforce governance and security controls; audit actions involving money and personal data.
Seniority
Senior, hands-on IC
