AI Platform Engineer: Enterprise AI Foundations & RAG

Landing Point; Village of Pelham (NY); On-site; USD 114,000 - 162,000; Full time

Job summary

Landing Point is seeking an AI Platform Engineer in New York to advance enterprise AI capability, moving from vendor-led to internal operations. You will build reusable AI foundations, RAG pipelines, embeddings services, and memory/prompt systems for compliant, scalable AI products.

You’ll work closely with backend teams to instrument production-ready pipelines on AWS, implement telemetry, and ensure secure, repeatable deployments across knowledge sources and agents.

Qualifications

• 7+ years of software/platform engineering with AI/ML or data-intensive systems.
• Experience with RAG, vector search, embeddings, and retrieval pipeline design.
• Proficient in Python and production systems on AWS/Azure/GCP.

Responsibilities

• Build and mature shared engineering foundations for AI products.
• Develop Retrieval-Augmented Generation (RAG) pipelines as reusable services.
• Create a centralized embeddings service and vector index management.
• Establish a memory bank for persistent, identity-scoped memory.
• Design context assembly logic for reusable prompts.
• Implement content ingestion and processing pipelines for knowledge sources.
• Develop prompt and configuration management systems for versioning.
• Create a shared PII detection and redaction library.
• Build a platform SDK and golden-path templates for compliant deployment.
• Integrate evaluation hooks for quality checks in AI products.
• Implement telemetry for usage, performance, and quality signals.
• Align identity and access integration with enterprise standards.
• Standardize deployment patterns and support practices for AI products.

Skills

RAG design

Vector search

Embeddings

CI/CD

Python

AWS

Production services

APIs

Observability

Memory management

Tools

Python

CI/CD

Vector databases

AWS

Job description

Landing Point is seeking an AI Platform Engineer in New York to advance enterprise AI capability, moving from vendor-led to internal operations. You will build reusable AI foundations, RAG pipelines, embeddings services, and memory/prompt systems for compliant, scalable AI products.

You’ll work closely with backend teams to instrument production-ready pipelines on AWS, implement telemetry, and ensure secure, repeatable deployments across knowledge sources and agents.