The opportunity
At Klaviyo, we believe the future of software lies not only in tools that help people work more efficiently, but in intelligent systems that can take action, learn from outcomes, and improve customer experiences over time.
What you'll do
Build and improve reliable backend systems and APIs that power AI-driven customer experiences.
Develop production agentic features involving tool use, context management,: retrieval, structured outputs, orchestration, and multi-step workflows.
Contribute to solving applied AI problems across retrieval and RAG,: grounding, hallucination mitigation, model selection, and choosing between LLM-based, deterministic, or hybrid approaches.
Build and use evaluation approaches including representative datasets,: automated and human evaluation, regression testing, qualitative error analysis, and production signals.
Improve system reliability through guardrails, retries, fallbacks,: observability, monitoring, and thoughtful failure handling.
Build asynchronous and distributed processing workflows that support AI workloads at scale.
What they're looking for
- You have 3+ years of professional software engineering experience , with: experience building backend systems or distributed applications.
- You have hands-on experience building or contributing to generative AI or: agentic AI applications , ideally used by real users or in production environments.
- You are proficient in Python and have experience with modern backend frameworks such as FastAPI or Django.
- You have experience with asynchronous processing or distributed task/event: systems such as Celery, Kafka, SQS, RabbitMQ, or Redis.
- You have working knowledge of databases, data modeling, APIs, and persistence: patterns used in production systems.
- You are comfortable working in cloud environments and have experience with: technologies such as AWS, containers, Kubernetes, infrastructure automation, or CI/CD systems.
- You can reason about tradeoffs among quality, latency, cost, reliability, and: implementation complexity, and know when to seek additional technical context.
- You are comfortable working through ambiguity, breaking larger problems into: smaller pieces, and making progress without every requirement being fully specified.
