On-Site AI Platform Engineer for GenAI Systems

lgads; Denver (CO); On-site; USD 120,000 - 180,000; Full time

Job summary

LG Ads is seeking an AI Platform Engineer to join our AI team and help build the in-house platform powering generative AI agents deployed business wide. You will contribute to the end-to-end stack, including LLM serving, RAG pipelines, and the APIs and infrastructure that put agents into production.

The role is hands-on: you'll write production Python, integrate with services like AWS Bedrock, and instrument systems for observability.

Qualifications

• Proven experience designing and developing Generative AI agents.
• Strong expertise in intent detection and complex query decomposition.
• Demonstrated experience with context engineering for AI models.
• Knowledge of LLMs and enterprise deployments (e.g., OpenAI, Claude, Llama 4 Maverick).

Responsibilities

• Build and maintain LLM-powered services and APIs (FastAPI, webhooks, LangGraph).
• Develop evaluation harnesses and offline/online eval pipelines to measure quality.
• Instrument services with logging, tracing, and metrics for observability.
• Design intelligent AI agents capable of intent recognition and decomposing queries.
• Implement context engineering to leverage memory and knowledge base.

Skills

Generative AI agents

Intent detection

Context engineering

LLMs

AWS

Databricks

RAG systems

Python

FastAPI

Education

Bachelor's or Master's in CS/AI/ML

Tools

LangGraph

AWS Bedrock

vector stores

Databricks

Snowflake

Job description

LG Ads is seeking an AI Platform Engineer to join our AI team and help build the in-house platform powering generative AI agents deployed business wide. You will contribute to the end-to-end stack, including LLM serving, RAG pipelines, and the APIs and infrastructure that put agents into production.

The role is hands-on: you'll write production Python, integrate with services like AWS Bedrock, and instrument systems for observability.