Staff AI Platform Engineer — Remote, Equity, Growth

Syndio; New York (NY); Hybrid; USD 205,000 - 225,000; Full time

Benefits offered by this job

Equity

Flexible vacation

Medical insurance

Dental insurance

Vision insurance

Life Insurance

Disability insurance

Remote-friendly in US

Job summary

Syndio’s AI platform team is hiring a staff-level engineer to own major runtime surfaces and grow the platform end-to-end. You will design, ship, and operate key backend services with a small, autonomous team, collaborating with product-team owners through the platform’s contribution seams.

You will work on the agent loop, tool integration, memory, and eval infrastructure, ensuring operability, compliance, and scalable cross-team impact across production systems.

Qualifications

• 5+ years building production backend systems.
• Experience shipping LLM-powered systems in production.
• Design for operability: compliance, tracing, evals, and kill switches.
• Own a technical domain with API design and end-to-end ownership.
• Strong written communication and cross-team collaboration.

Responsibilities

• Develop core runtime surfaces of syndi-api (agent loop, tool registry).
• Grow the eval system for production traces and detectors.
• Maintain production observability and incident response.
• Review product teams' tool wrappers and evals; update GET /tools.
• Ensure compliance and legal requirements are integrated into design.

Skills

Backend development

Python

Relational databases

Cloud infrastructure

LLM-powered systems

Operability & compliance

Technical ownership

APIs design

Tools

Datadog

Kubernetes

Postgres

Claude on Vertex

GCP

Job description

Syndio’s AI platform team is hiring a staff-level engineer to own major runtime surfaces and grow the platform end-to-end. You will design, ship, and operate key backend services with a small, autonomous team, collaborating with product-team owners through the platform’s contribution seams.

You will work on the agent loop, tool integration, memory, and eval infrastructure, ensuring operability, compliance, and scalable cross-team impact across production systems.