Senior AI Engineer

Guidepoint; Toronto; Hybrid; CAD 175,000 - 210,000; Full time

Benefits offered by this job

Paid time off

Company RRSP match

LinkedIn Learning access

Job summary

Guidepoint in Toronto is building applied AI across its research platform. We're hiring an engineer to move working prototypes to production, shaping the architecture as the product scope grows, with broad ownership and close collaboration with product and leadership.

This hybrid role covers real-time conversational AI, LLM orchestration, retrieval and grounding, and end-to-end ownership (Kubernetes/Azure).

Qualifications

• 6+ years of software engineering with 2+ years building LLM-powered products in production.
• Experience with real-time or streaming systems and low-latency workloads.
• Familiarity with agent/LLM frameworks and vector-db based retrieval.

Responsibilities

• Real-time conversational AI: voice- and chat-based agents with low latency.
• LLM orchestration: multi-turn agent goals with grounded outputs.
• Multi-channel session management with channel handoffs.
• Retrieval and grounding using large internal data assets.
• Evaluation infrastructure with metric-driven governance.
• End-to-end ownership: design, deploy (Kubernetes/Azure), operate systems.
• Design and optimize LLM pipelines and cost/latency tradeoffs.
• Build eval loops and gate releases on metrics.
• Integrate third-party AI and voice vendors behind clean abstractions.
• Collaborate with product and compliance to encode domain rules.
• Establish engineering patterns for growing team.

Skills

TypeScript

Python

Real-time systems

WebSockets

LangGraph

LangChain

CrewAI

Vector databases

Tools

Kubernetes

Azure

Job description

Guidepoint is investing in applied AI across its research platform. We're building conversational AI systems that interact with our global expert network at scale — combining real-time voice, LLM-driven orchestration, and retrieval over large proprietary datasets.

You'll be an early engineer on a new initiative: taking working prototypes to production and shaping the architecture as the product scope grows. This is a hands-on role with broad ownership, close to product and leadership.

This role is hybrid in our Toronto Office

What You'll Do:

• Real-time conversational AI: voice- and chat-based agents with low-latency requirements, built on modern telephony and real-time media infrastructure.
• LLM orchestration: agentic systems that pursue goals over multi-turn conversations, with hard behavioral guarantees enforced in code — not just prompts.
• Multi-channel session management: stateful user interactions that move seamlessly across channels.
• Retrieval and grounding: connecting LLM systems to large internal knowledge assets, with structured data flowing back.
• Evaluation infrastructure: measuring conversational quality against human baselines and gating rollouts on metrics, not vibes.
• Own services end-to-end: design, implementation, deployment (Kubernetes/Azure), and operations, including latency-sensitive real-time workloads.
• Design and tune LLM pipelines: context engineering, structured outputs, model selection, cost/latency tradeoffs across vendors.
• Build the eval loop and treat quality as a number: define metrics, run experiments, gate releases on them.
• Integrate third-party AI and voice vendors behind clean abstractions so providers stay swappable.
• Partner with product and compliance stakeholders to encode domain rules into the system.
• Set engineering patterns for a growing team: code review, observability, incident habits.

What You Have:

• 6+ years of software engineering, with 2+ years building LLM-powered products in production (not notebooks): orchestration, RAG/grounding, structured outputs, eval-driven iteration.
• Strong TypeScript or Python; comfortable working across both.
• Real-time or streaming systems experience: WebSockets, WebRTC, audio pipelines, or comparable low-latency work.
• Familiarity with agent/LLM frameworks such as LangGraph, LangChain, or CrewAI — hands‑on exposure is enough; we care that you know the landscape and when plain code beats a framework.
• Working familiarity with vector databases and embedding-based retrieval.
• Pragmatic product judgment: you scope prototypes, kill weak approaches with data, and ship.

Nice-to-have:

• Knowledge graphs or large-scale search/retrieval systems.
• Regulated or compliance‑sensitive domains (healthcare, finance).
• Eval harnesses or LLM‑as‑judge systems.

What We Offer:

The annual base salary range for this position is175,000-210,000 CAD.

Additionally, this position is eligible for an annual discretionary bonus based on performance.

Compensation

$175,000 - $210,000 CAD

You will also be eligible for the following benefits:

• Paid time off
• Company RRSP match
• Development opportunities through the LinkedIn Learning platform

About Guidepoint:

Guidepoint powers end-to-end research workflows for the world’s best research teams.

Backed by a global network of more than2 million experts and over 1,600 employees,Guidepoint delivers real‑time access to expertise, primary research, and actionable knowledge that help organizations make informed decisions. Through consultations, surveys, events, proprietary content, and AI‑enabled tools, we support every stage of the decision‑making process—from developing hypotheses and gathering insights to validating assumptions and building conviction for critical decisions.

At Guidepoint, our success relies on the diversity of our employees, experts, and clients, which enables us to foster meaningful connections and a broad range of perspectives. We are committed to creating an inclusive and welcoming environment where individuals of all backgrounds, identities, and experiences can contribute and succeed.