Job DescriptionWe are hiring an Applied AI Developer to build production systems powered by Large Language Models. You will design and ship tools that automate internal workflows and support client-facing work. The role is backend-heavy: you will write Python, build agentic operations that chain model outputs together, and build the infrastructure around them.
This is not an ML role. No model training, no fine-tuning, no weights. You work with existing generative AI services and the tools they expose.
What You'll Do: - Build and maintain AI-backed tools. Take a problem through scoping, implementation, deployment, and ongoing iteration. Projects vary in scale from single-purpose automations to larger pipelines that support multiple teams.
- Own deployed work. Tools that people actually use, measured by real usage and outcomes. You care what happens after launch, not just whether it ran once.
- Design agentic workflows. Chain LLM calls into pipelines rather than relying on one-shot prompts. Coordinate agent teams, handle asynchronous jobs, and build checkpoints for human review at the right points.
- Plan for failure modes. AI systems need guardrails: validation against known data, human review gates, continuous monitoring, and fallbacks when models produce bad output. You think about reliability from the start, not as a patch after the fact.
- Match the approach to the problem. Different tasks call for different models, different prompting styles, and different orchestration patterns. You form opinions from daily use and can justify your choices.
- Ship quickly. Turn a working idea into a deployed system in days, not months.
- Communicate across audiences. Write clearly for technical peers and non-technical stakeholders. Present work to internal teams and external audiences when needed
QualificationsRequired: - 3+ years of experience building backend applications or internal tools in Python, including API integrations, state handling, and maintainable service design.
- Hands-on experience integrating LLM APIs into an application, product, or internal tool, with evidence of shipping multi-step AI workflows beyond one-shot prompting.
- Demonstrated experience evaluating AI output quality using methods such as blind testing, LLM-as-judge scoring, hallucination checks, or structured human review in a production or pilot setting.
- Experience designing modular systems with clear inputs, outputs, and reusable components, supported by examples of deployed tools, automation pipelines, or shared internal services.
- Ability to explain technical decisions to both technical and non-technical audiences, including presenting recommendations, tradeoffs, or results to internal stakeholders.
Desired:- Comfort and enthusiasm for using AI as a regular part of how work gets done.
- Experience working with multiple LLM providers, including Anthropic, OpenAI, and Google Vertex AI / Gemini, with clear examples of when and why different models were selected.
- Experience deploying applications or services in Google Cloud or AWS, including production, staging, or internal-use environments.
- Portfolio of AI projects, personal or professional, that demonstrates agentic workflows, tool-building, evaluation discipline, or applied product development.
- Exposure to healthcare or pharma environments, including regulated, scientific, or complex domain contexts, is considered an asset.
Additional InformationThis posting is for a newly created role at Klick. The base salary range for this position is between CAD $100,000 - $120,000. The final amount offered will be determined based on several factors such as a candidate's work location, their unique skill set, education, and prior work experience.
#LI-Hybrid #LI-JP1
