4 days ago
Toronto, CanadaEntry Level / Mid Level
Responsibilities
- Build evaluation platform features for dataset creation and versioning, golden datasets, synthetic test data, and reusable metric templates.
- Implement agent scoring using code-based checks, LLM-as-judge, tool-call accuracy, grounding checks, human review, and evaluation statistics.
- Run evaluations before releases, after prompt, model, or tool changes, and on production agents at scale.
- Build traceability for tested agent, model, prompt, and dataset versions, including release approval records.
- Develop trust controls for agent identity, per-user access, tool permissions, guardrails, and data boundaries.
- Perform adversarial testing and red-teaming for prompt injection, out-of-scope requests, and data-boundary issues.
- Investigate agent failures and performance problems using logs and traces, and build end-to-end, load, latency, and diagnostic tooling.
- Convert production failures and user feedback into regression tests while writing tested, reviewed, documented, secure, privacy-conscious, and responsible-AI-compliant code.
Requirements
- 1–4 years of experience in AI/ML or software engineering; internships and applied research count.
- Bachelor’s degree in computer science, engineering, data science, mathematics, or a related field, or equivalent experience.
- Proficiency in Python with experience in version control, testing, and code review.
- Experience building backend services or platform features.
- Hands-on experience building evaluation or test systems for ML or LLM applications and reading failures from logs or traces.
- Working knowledge of LLM applications, including prompting, retrieval, and agents.
- Working knowledge of sampling, confidence intervals, variance across runs, and reviewer agreement measurement.
- Ability to write SQL and analyze results, along with clear written and verbal communication.
- Preferred: evaluation or observability features used at scale, LLM evaluation and observability tools, OpenTelemetry, red-teaming, OAuth 2.0, OIDC, delegated access, performance or load testing, MCP, A2A, Google Cloud, Vertex AI, GKE, Kubernetes, NIST AI RMF, ISO 42001, or a related master’s degree.
Benefits
- Targeted base pay for the Toronto, Canada location is CAD 102,000–152,000 annually, excluding bonus, equity, and benefits.
- Employee Assistance Program.
- Healthcare, life, disability, and optional benefit plans for eligible employees and families.
- Equinix-sponsored retirement or savings plans, including DCPP, RRSP, and TFSA.
- Vacation, personal time, and paid holidays.
- Disability accommodations are available during the employment process.
Tech Stack
Categories
About Equinix
Equinix is a public digital infrastructure company that operates a global platform of colocation and interconnection data centers for enterprises, cloud and network providers. It sells space, power, and connectivity, plus services such as Equinix Fabric, Network Edge, and Equinix Metal for hybrid multicloud and edge deployments. Founded in 1998 and headquartered in Redwood City, California, it is listed on NASDAQ (EQIX) and runs hundreds of IBX facilities across major metros worldwide.