06 Aug
|
Socket.dev
|
Toronto
06 Aug
Socket.dev
Toronto
Role Overview As aSenior Platform Engineer , you will help design, build, and evolve Compass Digital Labs'AI platform for LLM-powered applications and agentic systems . You will create secure, scalable, production-grade capabilities for orchestration, retrieval, tool integration, evaluation, observability, and governance. Working closely with platform, data, product, security, and engineering teams, you will enable AI copilots, operational automation, and intelligent customer experiences across our digital ecosystem. Key Responsibilities Design and operate the core platform capabilities that powerLLM applications, copilots, and agentic workflows across multiple environments. Architectsingle-agent and multi-agent execution patterns , including tool calling, workflow routing, state management, and human-in-the-loop checkpoints. Build and maintain a secureintegration layer that connects models to internal APIs, data products, and enterprise systems using patterns such asModel Context Protocol (MCP), OpenAPI-defined tools, and event-driven services . Developretrieval and knowledge capabilities that support grounded responses, including document ingestion, chunking, embeddings, vector search, metadata filtering, reranking, and source attribution. Establishevaluation frameworks and regression tests for response quality, task success, reliability, and safety; use offline and online evals to continuously improve production performance. Implementguardrails and governance controls for identity-aware access, PII handling, content safety, prompt and tool security, auditability, and compliance. Create end-to-endobservability for prompts, tool invocations, agent traces, latency, failure analysis,
and token or cost usage to support debugging and production operations. Automate platform provisioning and deployment usingTerraform, containers, CI/CD, and cloud-native services . Optimizemodel selection, throughput, latency, resilience, and cost efficiency across AI workloads. Collaborate with data and ML teams to expose governed structured and unstructured data to AI applications in a safe, reusable way. Help define reusable standards, platform patterns, and engineering best practices for building reliableAI and agent-based systems at scale. Qualifications Proven experience building or operatingproduction AI/LLM platforms , developer platforms, or complex distributed systems. Strong hands-on experience withPython and API or service development; experience withTypeScript, Go, or Java is a plus. Experience designingagentic systems or advanced LLM applications that usetool calling, workflow orchestration, retrieval-augmented generation (RAG), and state management . Familiarity with modern agent frameworks and platforms such asOpenAI Agents SDK, Amazon Bedrock Agents, LangGraph, or similar tooling . Strong understanding ofvector search, embeddings, knowledge base design, ranking/reranking, and grounded generation . Experience withAWS and up-to-date platform infrastructure, including containers, serverless services, Kubernetes, networking, and IAM.
Experience withTerraform or similar Infrastructure-as-Code tools and strongCI/CD automation practices. Understanding ofevaluation, prompt testing, offline benchmarks, and release guardrails for AI systems. Hands-on experience withobservability tooling for logs, metrics, tracing, and incident response. Strong grasp ofsecurity, privacy, and governance for AI systems, including secrets management, RBAC, data protection, and responsible AI controls. Ability to work cross-functionally with product, data, ML, and platform teams and translate emerging AI capabilities into reliable platform services. Bachelor's degree or equivalent inComputer Science, Engineering, or a related field . Nice to Have Experience building internal developer platforms or self-service tooling for AI teams. Experience with real-time inference, streaming workflows, or event-driven architectures. Familiarity with data platform concepts such asdbt, Spark, Apache Iceberg, or data product design . Background in hospitality, retail, or large-scale enterprise environments. Position Details Position Title: Senior Platform Engineer Salary: 130,000.00 - 160,000.00 Perks: Bonus Eligibility, 4 Weeks Vacation, RRSP and more! Employment Type: Full Time, Permanent Hybrid: 3 Times a Week - Toronto/ Mississauga Remote: Canada Only *In accordance with provincial legislation and our commitment to transparent hiring practices, the compensation range for this position is provided. Final compensation will be determined based on qualifications, experience, and internal equity. Canadian work experience is not required. Please note that artificial intelligence tools are utilized in the applicant screening proces* s. #J-18808-Ljbffr
📌 Senior Platform Engineer (Toronto)
🏢 Socket.dev
📍 Toronto