Senior Frontend Software Engineer, AI UX

Pebl

Get hot jobs first on Telegram

New positions appear faster in our channel

Location: Toronto, Ontario, Canada
Job Type: full-time
Work Format: 🏢 Hybrid
Salary: CA$140K – CA$200K • Offers Equity
Posted: August 3, 2026

Job Description

Senior Frontend Software Engineer, AI UXLocation: Toronto, Ontario, CanadaEmployment Type: FullTimeLocation type: HybridDepartment: TechnologyCompensation: CA$140K – CA$200K • Offers EquityOur job titles may span more than one career level. The base pay depends upon many factors, such as training, transferable skills, work experience, business needs, and market demands. The base pay range is subject to change and may be modified.Apply Now

Purpose in Every Position

Pebl puts a world of talent at your fingertips. With our AI-powered Global Work Platform™, companies can hire, pay, and manage employees in 185+ countries—removing risk, red tape, and guesswork from global growth. Backed by more than a decade of compliance leadership and local expertise, Pebl helps businesses move fast, stay compliant, and scale with confidence. With Pebl, companies everywhere can hire great talent anywhere.

Where Your Work Moves the Needle.

At Pebl, every team member drives our success. Joining us means more than filling a role—you’re accountable for results and impact. Our values guide how we operate, execute, and collaborate across borders. By putting them into action, you’ll help us scale faster, compete harder, and lead the future of global work.

What Makes You a Great Fit

Our mission at Pebl is to simplify global employment, enabling companies to hire, manage, and retain talent anywhere in the world. We’re not just adding a chatbot to our product — we’re rethinking what it means for software to work with you, not just for you. Our AI & Knowledge team is on the front lines of that shift, building Alfie, our conversational AI assistant, and we’re looking for a Senior Full-Stack Software Engineer who wants to help define what AI-native user experience looks like — not follow a playbook that already exists, because it doesn’t yet.

We’re looking for someone who is strongest in frontend/product engineering and excited about building conversational AI interfaces that real users interact with directly. You’ll help shape the experience around streaming responses, wrong-answer recovery, fallback states, user trust, and human-in-the-loop moments.

This is not primarily a backend AI infrastructure, RAG platform, internal automation, or AI-assisted developer tooling role; the core need is someone who can help drive the user-facing AI experience.

How You’ll Make an Impact

Design and build full-stack features for our conversational AI assistant, with particular depth and ownership on the frontend/UX side.
Apply hands-on experience with LLM-based and agentic systems — prompt design, tool/function calling, multi-step agent reasoning, evaluation — to shape both how the assistant behaves and how that behavior surfaces in the UI.
Bring product taste and a strong point of view on what makes an AI-driven experience great — push for a better UX rather than shipping “good enough.”
Push the boundaries of what conversational and generative AI interfaces can feel like — prototype and propose new interaction patterns as the underlying models and agent capabilities evolve.
Help shape the future of how people interact with software at Pebl — you’ll be working at the edge of what’s possible in conversational and agentic UX, not maintaining what’s already been figured out.
Build and maintain both frontend and backend components (TypeScript/React on the frontend; comfortable enough on the backend to design clean contracts and APIs that support agentic workflows).
Lead by example in clean, maintainable code across the stack; mentor junior team members and foster a culture of constant learning and improvement.
Contribute to technical discussions, design reviews, and code reviews to maintain high engineering standards.
Troubleshoot issues end-to-end (frontend and backend) in production, including AI-specific failure modes (e.g., bad model output, latency, dropped tool calls).

Let’s Connect If You Have

8+ years of professional software engineering experience, full-stack, with demonstrated strength and a clear preference for frontend/UX work.
1+ years of hands-on experience building LLM-powered or agentic products — not just calling an API, but designing how an agent reasons, uses tools, and hands control back to the user.
Experience building interfaces for AI-powered or agentic products — conversational UIs, copilots, assistants — including exposure to generative/dynamic UI techniques where the interface adapts to model behavior.
Solid understanding of LLM design patterns, prompt engineering, and observability/instrumentation for agentic systems.
Strong command of modern frontend (React/TypeScript) paired with a solid understanding of how frontends integrate with backend services, APIs, and real-time/streaming data.
A track record of helping build products beyond standard CRUD apps and dashboards — something with real craft, polish, or a distinctive user experience.
Comfort working across the full stack when needed (backend, infra) — this isn’t a pure frontend role.
A lean mindset — focus on delivering customer value by minimizing waste, optimizing workflows, fostering continuous improvement, and prioritizing quick iteration with quick feedback cycles.
Excitement for working in a space that’s evolving rapidly, where the best patterns for AI-driven UX are still being discovered — and a desire to help discover them.

Our Commitment to You

At Pebl, we’re committed to supporting our team with comprehensive rewards and benefits designed to meet diverse needs across roles and locations. Our core offerings include:

Flexible Time Off – Take the time you need to recharge.
Parental Leave – Support for growing families.
Health and Dental Insurance – Where applicable, to cover you and your loved ones.
Retirement Savings + Employee Incentive Plan – Plan for the future while sharing our success.

Please visit our career page for more information.

Pebl is an Equal Opportunity Employer.

We power global teams and believe diverse perspectives drive innovation and impact. Employment decisions at Pebl are based on qualifications, merit, and business needs. We do not discriminate on the basis of race, color, religion, sex (including pregnancy, sexual orientation, or gender identity), national origin, age, disability, genetic information, veteran status, or any other status protected by applicable law. We’re committed to fostering an inclusive culture where every teammate can thrive and do the best work of their career—anywhere in the world.

🎯 Who is this job for?

Senior-level frontend-focused full-stack software engineers with 8+ years of experience, strong React and TypeScript skills, and a solid understanding of backend APIs, infrastructure, and real-time streaming.

They should be experienced with LLM-powered or agentic products, including prompt design, tool calling, multi-step reasoning, evaluation, observability, and conversational or generative user interfaces.

The role suits people familiar with designing polished AI UX, handling streaming responses and failure states, troubleshooting production issues across the stack, prototyping interaction patterns, and mentoring engineers.

💬 Potential Interview Questions

How would you design a React and TypeScript conversational UI that supports token streaming, partial responses, and cancellation?

I would model each message as a stateful entity with statuses such as pending, streaming, completed, failed, and cancelled. The client would consume a streaming API, append validated chunks incrementally, support AbortController cancellation, and preserve recoverable state if the connection drops.

Which transport would you choose for streaming LLM responses, and how would you handle reconnection?

Server-Sent Events are often a good fit for unidirectional token streaming, while WebSockets are preferable when the client and server need frequent bidirectional events. I would include request and event IDs, resume offsets where possible, exponential backoff, duplicate protection, and a clear UI state when recovery is not possible.

How would you design the frontend contract for an agent that performs multi-step tool calls?

The API should expose structured events such as reasoning status, tool invocation, tool result, user approval request, assistant message, and error. I would use discriminated TypeScript unions so every event is explicitly handled and the UI can render progress, permissions, and failures without relying on fragile text parsing.

How should an AI assistant recover when the model produces an incorrect answer or a tool call fails?

The interface should make uncertainty and failure visible without exposing confusing internal details. It can offer retry, edit-and-resubmit, clarification, source or tool-result inspection, human escalation, and a way to correct the assistant while retaining the conversation context.

How would you implement human-in-the-loop approval for sensitive agent actions?

The backend should pause execution and return a structured approval request describing the intended action, affected data, and potential consequences. The frontend should present explicit approve, reject, and modify actions, while the server independently validates authorization and prevents client-side approval from bypassing policy.

What techniques would you use to prevent prompt injection and unsafe tool usage in an agentic product?

I would treat model output as untrusted, enforce tool schemas and server-side authorization, isolate system instructions from retrieved or user-provided content, and apply allowlists, validation, rate limits, and confirmation gates. Sensitive operations should be auditable and require deterministic policy checks outside the model.

How would you design generative UI components that adapt to different agent responses while remaining maintainable?

I would define a constrained catalog of typed UI primitives and render them from validated response schemas rather than allowing arbitrary model-generated markup. This preserves flexibility while maintaining accessibility, security, consistent interaction patterns, and compatibility with analytics and testing.

How would you instrument and evaluate the quality of a conversational AI experience?

I would capture latency to first token, completion time, tool success rates, abandonment, retries, escalation, correction frequency, and task completion. Traces should correlate frontend interactions with backend model and tool calls, while offline and production evaluations measure accuracy, groundedness, safety, and user satisfaction.

How would you optimize perceived and actual latency in a React AI interface?

I would stream responses immediately, show meaningful progress states for tool calls, optimistically render user messages, and avoid blocking unrelated UI. On the backend, I would reduce unnecessary model calls, parallelize independent tools, cache safe results, and establish timeouts with graceful fallbacks.

How would you troubleshoot a production issue where users see incomplete responses or dropped tool calls?

I would trace a request end to end using correlation IDs across the browser, API, model gateway, and tool services. I would compare client event logs with server traces, inspect timeouts and connection termination, reproduce with the same conversation state, and then add targeted metrics, retries, or protocol safeguards based on the failure mode.

📋 Job Summary

Pebl is an AI-powered Global Work Platform helping companies hire, pay, and manage talent in more than 185 countries. As a Senior Frontend Software Engineer, you’ll shape Alfie, Pebl’s conversational AI assistant, building polished, trustworthy interfaces with React, TypeScript, streaming data, APIs, and agentic AI technologies while contributing across the full stack. This is a hybrid full-time role based in Toronto, offering CA$140K–CA$200K plus equity. Apply to define emerging AI-native UX patterns, influence a globally impactful product, and work at the forefront of how people interact with software.