Description

You will own the end-to-end deployment and operation of advanced AI agent systems.

This role is on-site.

Responsibilities

• Design multi-agent architectures, defining agent roles, tooling, memory strategies, and supervisor policies for safe collaboration.
• Build high-quality Retrieval Augmented Generation (RAG) pipelines, implementing ingestion, chunking, embeddings, and evaluation metrics like groundedness.
• Productionize ML/LLM workloads on AWS, utilizing services such as Bedrock, Lambda, API Gateway, and Step Functions.
• Automate MLOps/LLMOps pipelines using GitOps, containerization (Docker/Kubernetes), and infrastructure-as-code practices.
• Instrument telemetry, build operational dashboards, and implement continuous offline/online evaluation loops for system health.

Required Skills

• 5+ years of proven experience building agentic systems and production RAG pipelines.
• Strong background in cloud infrastructure for AI/ML workloads, specifically AWS (Bedrock, S3, DynamoDB).
• Proficiency with CI/CD, Git, Docker, and Kubernetes.
• Experience implementing infrastructure-as-code principles and managing IAM/secrets.
• Knowledge of the MLOps/LLMOps lifecycle, including data governance and model accountability.
• Familiarity with vector databases and LLM platforms.

Preferred Skills

• Bachelor's degree in Computer Science, Data Science, Engineering, or equivalent experience.
• Solid problem-solving and cross-functional collaboration skills.

Key Skills

Education

Bachelor's degree