**Job Title: Senior AI Platform Engineer

Client Location: Canada

Work Location: Remote** **Work Schedule: Monday to Friday (9:30 PM to 6:30AM IST)

Experience Level: 5+ Years** About The Role As our Senior AI Platform Engineer, you'll build the platform that turns our AI capabilities into reliable, secure, and useful product experiences. You'll own the infrastructure and engineering patterns behind our AI-powered concierge, including how we work across multiple models, fall back to on-device capabilities, safely generate outputs, and connect AI to the systems and data it needs.

This is a technical role for an engineer who is excited about building AI systems that are more than a demo. You'll help create the foundations that make AI experiences reliable, deterministic where they need to be, secure, and capable of operating at scale.

What You'll Do

- Design and build the multi-model AI platform that powers our AI concierge and other AI-powered product experiences.
- Develop the infrastructure and orchestration layer that allows us to work with multiple AI models and select the appropriate model or capability for a given task.
- Build robust fallback strategies, including on-device AI capabilities, to ensure our experiences remain useful and resilient when cloud-based models are unavailable.
- Develop constrained-generation systems that ensure AI outputs follow defined rules, structures, and product requirements.
- Build deterministic validation and decision gates behind AI-powered experiences, ensuring that the system can reliably determine when an AI output is safe and appropriate to use.
- Build the evaluation infrastructure our AI features depend on, including tracing, offline evaluation harnesses, and automated regression suites that show whether a prompt, model, or configuration change improved quality or degraded it — before it reaches customers.
- Manage how models and prompts change over time, including versioning,



staged rollout, and detecting quality regressions when a provider updates or retires a model we depend on.
- Help build adaptive user experiences that respond intelligently to AI-generated results while maintaining predictable product behaviour.
- Design and implement our Model Context Protocol (MCP) surface, including robust authentication, authorization, and role-based access control.
- Build secure mechanisms for AI systems to access tools, data, and product capabilities while ensuring users and systems can only access what they are authorized to access.
- Establish engineering patterns and infrastructure that make it easier for product teams to safely build and ship AI-powered capabilities.
- Define how we use AI safely in our own development process, including the review practices, boundaries, and tooling that keep AI-assisted code at a volume and quality our engineers can genuinely verify.
- Monitor and improve the reliability, performance, latency, and cost of our AI systems.
- Work closely with product, data, and application engineering teams to integrate AI capabilities into customer-facing experiences.
- Stay current with rapidly evolving AI infrastructure, model capabilities, and engineering practices and help determine where new technologies can meaningfully improve our products.

What We're Looking For

- Significant experience building and operating production software systems, with strong experience in AI/ML infrastructure or AI-powered applications.




- Experience working with multiple foundation models and understanding the practical differences between models, including their capabilities, limitations, latency, and cost.
- Strong software engineering fundamentals and experience designing reliable, maintainable production systems.
- Experience building AI orchestration, agentic systems, model gateways, or similar AI infrastructure.
- Solid understanding of techniques for controlling and validating AI output, including structured or constrained generation and deterministic validation.
- Experience evaluating AI systems beyond manual spot-checking — building evaluation sets, tracing, and automated regression testing, and using the results to make ship or no-ship decisions.
- Experience designing secure systems where AI agents or services interact with tools, APIs, and data.
- Strong understanding of authentication, authorization, and role-based access control, ideally in systems where permissions must be enforced at runtime.
- Experience with MCP or similar protocols for connecting AI systems to tools and data is highly valuable.
- Experience shipping AI features on mobile, or a track record of working closely with mobile engineers to do so. Familiarity with on-device inference using platform-provided models such as Apple Foundation Models or Gemini Nano is an asset.
- Strong understanding of distributed systems, APIs, observability, and production reliability.
- Comfort working in an environment where the technology is evolving quickly and the right solution isn't always obvious.
- A pragmatic approach to AI engineering—you understand that building a great AI product requires balancing model capability with reliability, security, performance, cost, and user experience.
- Excellent communication skills and the ability to collaborate closely with product managers, data engineers, and application engineers.

📌 Senior AI Platform Engineer (India)
🏢 Outsourced
📍 India