The ML Engineer – LLM Platforms & Assistants will design, build, and operate production-grade large language model (LLM) pipelines primarily within AWS-based environments. This role focuses on integrating OpenAI models into modular Python services, implementing Retrieval-Augmented Generation (RAG) and semantic search, and deploying scalable, secure, and observable AI assistants.
Key Responsibilities
• Design and maintain LLM integrations using OpenAI APIs within AWS environments.
• Build Python-based LLM services deployed on AWS compute platforms (ECS, EKS, Lambda, or EC2).
• Implement RAG workflows and semantic search using AWS data and storage services.
• Develop LangChain or agentic workflows supporting reasoning and tool use.
• Integrate LLM pipelines with ETL/ELT workflows and enterprise data systems.
• Deploy and integrate MCP servers and emerging orchestration tools.
• Apply AWS security best practices using IAM, KMS, and Secrets Manager.
• Implement monitoring and observability using CloudWatch and related tools.
• Migrate custom GPT solutions into production-grade AWS-hosted assistants.
Ideal Candidate Profile
• 4–7+ years in software, ML, or applied AI engineering.
• Strong Python proficiency.
• Experience with RAG and semantic search.
• Hands-on OpenAI LLM integration experience.
• Experience deploying systems in AWS (S3, Lambda, ECS/EKS, IAM).
Preferred Qualifications
• Experience with Amazon Bedrock.
• AWS data services: Glue, Athena, OpenSearch, Aurora.
• ETL/ELT pipeline development.
• LLM orchestration and reasoning workflows.
• Benchmarking and LLM evaluation.
• Infrastructure as Code (CDK, CloudFormation, Terraform).
Education:
• Bachelor’s degree in Computer Science, Engineering, Information Systems, or equivalent experience.
Machine Learning Engineer in manhattan at Unknown Company
This position is listed as full time and onsite.