AI Observability & Platform Engineer

Canada
Remote
Posted Sep 18, 2026
1 position

Opens LinkedIn

Employment type: Contract
Experience level: Senior · 5+ years
Posting language: English
Working hours: 40 hours per week
Seniority: Mid-Senior level
Application method: Direct apply is available

Job summary

Build and operate observability, reliability, and governance capabilities for enterprise GenAI and agentic applications. Implement end-to-end telemetry and monitoring for LLM performance, cost, and operational health using Kubernetes and various AI frameworks.

Job details

About GSPANN Headquartered in California, U.S.A., GSPANN provides consulting and IT services to global clients. We help clients transform how they deliver business value by helping them optimize their IT capabilities, practices, and. With five global delivery centers and 2000+ employees, we provide the intimacy of a boutique consultancy with the capabilities of a large IT services firm. Role: AI Observability & Platform Engineer Location : Remote-(Canada) Duration: Long term Role Overview We are looking for an experienced AI Observability & Platform Engineer to build and operate the observability, reliability, governance, and platform capabilities supporting enterprise GenAI and agentic applications. Key Responsibilities Build and operate observability for LLM gateways, model routing, MCP servers, agent runtimes, and AI platform services. Implement end-to-end telemetry using OpenTelemetry, Langfuse, metrics, logs, and distributed tracing. Monitor and analyze LLM/agent latency, errors, token usage, model performance, quality, evaluation results, and production behavior. Develop dashboards, alerts, and reporting for AI reliability, performance, quality, and operational health. Build AI cost and usage observability, including attribution by application, team, user, model, workflow, and environment across providers such as OpenAI, Anthropic, and Gemini. Establish observability and evaluation standards for LLM and agentic applications, including traces, prompts, responses, tool calls, evaluations, and regression signals. Support AI evaluation and monitoring through golden datasets, scoring, prompt/model comparisons, and production quality checks. Operate AI platform services on Kubernetes using Helm, Kustomize, GitOps, autoscaling, and progressive/zero-downtime deployments. Implement platform security, access control, secrets management, PII protection, guardrails, and audit logging. Enable observability across MCP, LangChain, LangGraph, CrewAI, Google ADK, and other agent frameworks. Build self-service capabilities, templates, and automation that allow development teams to onboard AI applications and agents efficiently. Partner with engineering teams to turn observability insights into platform improvements, reliability enhancements, and cost optimization. Technical Environment: AI/LLM Observability: Langfuse, OpenTelemetry, LLM tracing, AI evaluation AI Platforms: LLM gateways, model routing, MCP, agentic AI Cloud/Platform: Kubernetes, Helm, Kustomize, GitOps, APIs Monitoring: Prometheus, Grafana, Datadog or similar platforms AI/ML: OpenAI, Anthropic, Gemini, LangChain, LangGraph, CrewAI, Google ADK Engineering: Python/Java/Go, REST APIs, CI/CD Security: OAuth2/OIDC, JWT, RBAC, secrets management, PII/AI guardrails Working at GSPANN GSPANN is a diverse, prosperous, and rewarding place to work. We provide competitive benefits, educational assistance, and career growth opportunities to our employees. Every employee is valued for their talent and contribution. Working with us will give you an opportunity to work globally with some of the best brands in the industry. The company does and will take affirmative action to employ and advance in the employment of individuals with disabilities and protected veterans and to treat qualified individuals without discrimination based on their physical or mental disability status. GSPANN is an equal opportunity employer for minorities/females/veterans/disabled.

What you’ll do

Requirements

Requires experience in AI platform engineering with proficiency in OpenTelemetry, Kubernetes, and LLM observability tools. Candidates should be skilled in Python, Java, or Go and familiar with agent frameworks like LangChain and CrewAI.