2 months ago
Toronto, CanadaMid Level
Responsibilities
- Build components of a vendor-agnostic agent platform, including orchestration, tool use, memory, and runtime systems.
- Implement evaluation and reliability tooling such as metrics, harnesses, and pipelines for agent performance, robustness, and safety.
- Implement safety and governance controls including guardrails, policy enforcement, and human-in-the-loop review mechanisms.
- Develop data grounding, retrieval, and memory components for accurate and context-aware agents.
- Prototype agent behaviors involving planning, multi-step execution, and coordination of tools and services.
- Partner with product and engineering teams to implement agent-powered workflows.
- Apply and refine design patterns for secure, observable, and scalable agent systems.
- Contribute knowledge of LLMs, GPU computing, and model serving to technical implementation decisions.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Machine Learning/AI, or a related field, or equivalent practical experience.
- At least 2 years of professional software engineering experience in distributed systems, backend platforms, infrastructure, or comparable technical environments.
- Strong foundational knowledge of LLMs and agentic AI systems, including architectures, prompting, orchestration, tool use, and evaluation.
- Strong understanding of GPU computing and model-serving infrastructure, including relevant performance and cost trade-offs.
- Solid grounding in distributed systems fundamentals such as concurrency, fault tolerance, observability, and performance.
- Proficiency in at least one modern backend programming language and ecosystem, such as Java, Go, or Python.
- Comfort working with cloud-native infrastructure, APIs, and data services.
- Preferred experience with multi-agent systems, workflow orchestration, distributed coordination frameworks, agent platforms, LLM routing, caching, or fine-tuning pipelines.
- Preferred experience with evaluation frameworks, experimentation platforms, ML systems, AI safety, security or policy systems, retrieval systems, knowledge graphs, or enterprise data platforms.
- Strong technical performance demonstrated through professional work, research, challenging projects, open-source contributions, internships, or comparable experience.
Categories
About Socure
Socure builds an AI-driven digital identity verification and fraud prevention platform used by banks, fintechs, e-commerce, telecom, healthcare, and government agencies to automate KYC/AML, document verification, and risk decisioning. It sells enterprise APIs and workflows for onboarding, authentication, and payments fraud mitigation. Founded in 2012 and headquartered in Incline Village, Nevada, Socure is privately held and operates across regulated and high-volume digital markets.