Senior Software Engineer, AI Platform – US

Jobtailor; Calgary; On-site; CAD 120,000 - 180,000; Full time

Job summary

Jobtailor in Calgary seeks a senior backend engineer to build production systems powering Syndi's backend. You will work on the agent loop, tool execution and registry, memory and context management using Python, Postgres, Claude on Vertex, and GCP.

You will design for operability and compliance, implement tracing, eval infrastructure, and contribute to the GET /tools registry and drift-detection contracts, collaborating with product teams.

Qualifications

• 5+ years building production backend systems with Python and cloud infra on GCP/Kubernetes.
• Experience deploying LLM-powered systems in production and managing tool integration.
• Design for operability including compliance, tracing, evals, and kill switches.

Responsibilities

• Own a technical domain with API design, review cycles, and shipping with pager duty.
• Advance the platform by reviewing tool wrappers, GET /tools registry, and drift-detection contracts.
• Collaborate across teams with strong written communication and documentation.

Skills

Python

Relational Databases

Cloud Infrastructure

Kubernetes

LLM Integration

API Design

Incident Response

Compliance Engineering

Tracing

Eval Infrastructure

Tools

Postgres

Datadog

Syndi-API

Claude on Vertex

Job description

• Core runtime surfaces of syndi-api: the agent loop, tool execution and registry, memory, context management (Python, Postgres, Claude on Vertex, GCP).


• The eval system — offline gates and online detector/judge evals written onto production traces — and its growth as product teams adopt it.


• Production operation: observability (Datadog LLM Obs), incident response, the reliability of an agent surface real customers use.


• The platform's contribution seams: reviewing product teams' tool wrappers and evals, evolving the GET /tools registry and drift-detection contract.


• Clarifying, designing, and implementing compliance and legal requirements for Syndi.

Requirements

• 5+ years building production backend systems; deep comfort with Python, relational stores, and cloud infra (we're on GCP/Kubernetes).


• You've built LLM-powered systems in production — an agent loop, tool-calling integration, RAG, or eval infrastructure — and have opinions from the scar tissue.


• You design for operability: legal compliance, tracing, evals, and kill switches are part of the feature, not afterthoughts.


• You can own a technical domain with light supervision: propose direction in writing with clear API specs, take review, ship, and carry the pager for what you shipped.


• Strong written communication — our operating model runs on design docs and PR review across team boundaries.


• Nice to have: experience being the platform side of a platform/product relationship; SSE/streaming systems; compliance-adjacent engineering (data minimization, auditability); prior Staff scope.

Core Competencies

Demonstrates expertise in building production backend systems with a focus on Python, GCP, and compliance requirements. Capable of designing operable systems that integrate LLM technologies and ensure reliability and observability.

Highest-signal resume keywords

• Python Development


• GCP Infrastructure


• LLM-Powered Systems


• Production Backend Systems


• Strong Written Communication

ATS Optimization Keywords

Hard Skills

• Python


• Relational Databases


• Cloud Infrastructure


• Kubernetes


• LLM Integration


• API Design


• Incident Response


• Compliance Engineering


• Tracing


• Eval Infrastructure

Soft Skills

• Strong Written Communication


• Collaboration

Industry Keywords

• Compliance


• Observability


• Incident Response


• Data Minimization


• Auditability

Tools & Technologies

• Postgres


• Datadog


• Syndi-API


• Claude on Vertex