Senior Software Engineer, Agents

Replicant; Canada; Remote; CAD 120,000 - 180,000; Full time

Benefits offered by this job

In-person offsites

Tech & learning stipend

Remote by design

Health & wellness benefits

Equity with upside

Competitive compensation

Job summary

Replicant is deploying AI agents to transform customer service for enterprise clients. You will sit with customers to understand workflows, craft prompts, and build integrations to production. You’ll own the agent end‑to‑end, measure outcomes, and work across a small, highly visible team.

The role blends trusted advisory work with hands-on engineering, focusing on scalable, reliable AI agents and strong customer outcomes. Remote by design with international clients.

Qualifications

• Customer-facing communication and stakeholder management.
• Ability to map customer workflows and translate goals into concrete agent scope.
• Experience shaping LLM behavior through prompts and structured instructions.
• Nice-to-have: background in frontend/backend coding and integrations.

Responsibilities

• Own AI agents for assigned customers across the full lifecycle: discovery, design, build, evaluation, launch, and live operation.
• Map customer workflows and translate business goals into agent scope and success criteria.
• Design agent prompts and flows, iterate against transcripts and evals.
• Integrate agents with customer systems via APIs and tools, ensure reliability and proper auth.
• Build test sets covering happy/unhappy paths, measure quality, and harden for production.
• Monitor live conversations and tool calls; debug from logs and ship fixes.
• Provide feedback to Product to accelerate next agent builds.

Skills

Customer facing

Integration fluency

Prompt crafting

Coding experience

Tools

TypeScript

Python

SQL

Job description

At Replicant, we believe AI should work for people, starting with customer service. That's why we built a platform that helps contact centers resolve more requests, proactively identify issues, and improve agent performance with AI-powered conversation intelligence and AI agents that act like your best reps.

Our AI agents handle millions of calls every month for Fortune 500 companies and high-growth innovators. From processing payments to booking appointments and authenticating users, they help customers get what they need instantly, 24/7. Meanwhile, our real‑time conversation insights help contact center leaders coach better and improve every interaction.

We are leading the shift from legacy systems to AI-first service, powered by large language models (LLMs) and designed for enterprise scale, security, and empathy. If you're excited by the potential of LLMs, voice AI, and building category‑defining technology with a kind, ambitious team, you'll love it here.

Our customers don't buy software. They buy a working AI agent that answers their calls, resolves their customers' problems, and holds up in production. As a Senior Software Engineer, Agents on our Delivery team, you make that happen for specific customers: you sit with them to understand their workflows, design and write the agent's instructions and conversation behavior, build the integrations the agent calls as tools, and own the agent end to end from blank prompt to production. This is a customer-embedded engineering role, equal parts trusted advisor, integration builder, and prompt engineer, and you are measured on customer outcomes, not features shipped. It's also one of the most in-demand emerging skill sets in the market, and you'll build it on real production traffic, not demos, with real autonomy on a team small enough that your work is visible to customers and leadership alike.

What You'll Do

• Own AI agents for your assigned customers across the full lifecycle: discovery, design, build, evaluation, launch, and live operation.
• Sit with customers, map their workflows, and translate ambiguous business goals into a concrete agent scope: what the agent handles, what it escalates, and what success looks like. Uncover the customer's real business rules, including the unwritten ones, and pin them down so the agent enforces that business logic strictly.
• Design and write the agent's prompts, instructions, and conversation flows, and iterate against evals, real transcripts, and your own product taste for what a good conversation sounds like.
• Wire the agent into customer systems (CRMs, ticketing, internal services): call their APIs as tools, shape inputs and outputs so tool calls are reliable, and handle auth, errors, and edge cases. You won't build the customer's APIs, but you will tell them what the agent needs from an API, then test and validate what they deliver.
• Build test sets from real cases covering not just the happy path but unhappy paths, edge cases, and hallucination risks; measure agent quality and harden agents for production: guardrails, failure modes, latency, and cost.
• Monitor live conversations and tool‑call health, debug from logs and transcripts, and ship fixes under pressure.
• Feed recurring patterns and missing capabilities back to Product so each agent makes the next one faster to build.

What You'll Bring

• Customer‑facing strength. You can sit across from a customer, converse credibly, and earn trust quickly, including with skeptical stakeholders. You decompose ambiguous, sometimes politically loaded business problems into a concrete plan, communicate clearly with both technical and non‑technical audiences, and push back when a request is feasible but wrong.
• Integration fluency. You understand and can shape integration patterns: how to connect an agent to a customer's APIs, endpoints, and protocols, design clean tool schemas, and handle auth, errors, and edge cases so tool calls are reliable. You validate bespoke, sometimes under‑documented customer APIs before an agent depends on them, and you're comfortable with external and third‑party systems beyond the customer's own stack.
• Prompt and instruction craft. You can shape LLM behaviour through structure, instructions, and examples, you write instructions that are unambiguous and easy to follow, and you know why a prompt fails. You work eval‑first, and you bring product taste: a feel for what a good conversation sounds like, not just what passes the tests.
• Nice to have: general‑purpose coding experience (TypeScript, Python, SQL); prior forward‑deployed, solutions engineering, or customer‑embedded work; conversational AI, voice, or contact center domain experience; experience with LLM evaluation tooling and observability.

A computer science degree or a software engineering title is not required. If your background is systems administration, integration engineering, technical support, or anywhere else you learned how systems talk to each other by taking them apart, we want to hear from you.

For all full‑time employees, we offer:

• In‑person connection that counts: company‑wide offsites and smaller team gatherings designed to make remote work feel personal
• Tech & learning stipend: Conferences, books, courses — interested? We’ll fund them
• Remote by design: We’re distributed — no guilt about life events, we trust you to manage your calendar
• Health & wellness: Flexible vacations, paid sabbatical after 5 years, comprehensive benefits, plus a stipend to support your physical and mental well‑being
• Compensation that matches your impact: competitive salaries in the company you’re helping to build
• Equity with upside: We believe in shared ownership—You’ll own a real piece of a fast‑growing AI company

Our Values

Blade Runners

We take ownership and pride to influence the outcomes of our goals. We are successful, and like a Blade Runner, use the tools at our disposal to reach our objectives. We value open and honest communication and proactively seek feedback along the way. We are a company driven to grow and achieve both individually and as a team.

Bread Makers

We are humble and strive toward an egalitarian culture. No task is too big or too small. We work together to achieve our goals and develop our company mission. We believe that the whole is greater than the sum of its parts in everything that we do.

Självdistans (Self‑Distance)

Självdistans is Swedish for self‑distance. It’s the ability to critically reflect on oneself and one's relations from an external perspective. With this in mind, we act with objectivity and always remember that we are not our work. There’s no perfect science to growing a team or business, but we trust everyone at Replicant to point out our blind spots and humbly admit their own.

Replicant is proud to be an equal opportunity employer. We are committed to fostering an inclusive, diverse and equitable workplace that is built on trust, support and respect. We welcome all individuals and do not discriminate on the basis of gender identity and expression, race, ethnicity, disability, sexual orientation, colour, religion, creed, gender, national origin, age, marital status, pregnancy, sex, citizenship, education, languages spoken or veteran status. Accommodation is available upon request at any point during our recruitment process. If you require an accommodation, please speak to your talent acquisition partner or email us at [e-mail] and we’ll work to meet your needs.