Senior Backend Software Engineer

Why Cascade?

Cascade AI helps HR organizations transform how they operate with AI agents that automate critical HR functions, including support, open enrollment, onboarding, leave of absence, compensation, and more. Our agents execute processes and workflows, streamline HR operations, and deliver employees the help they need instantly and conversationally.

By combining LLMs with an organization's existing HR technology stack, Cascade agents streamline operations, improve employee experience, and unlock significant cost savings. Deployed globally across 30+ countries, supporting multilingual workforces.

Trusted by dozens of enterprise customers, including Fortune 100 companies. Backed by Gradient Ventures, Google's AI fund. Founded by two former Microsoft engineers through the MIT Sandbox Innovation program.

Role: Senior Backend Engineer

As a Senior Backend Engineer at Cascade, you will design, build, and own the core backend systems that power AI agents automating real HR work at scale — serving dozens of enterprise customers across 30+ countries, spanning industries from healthcare and energy to SaaS and cybersecurity, with employee populations ranging from 1,000 to 100,000+.

This is a high-impact, hands-on role where you'll drive architecture decisions, mentor engineers, and take end-to-end ownership of critical systems — from API design through production reliability.

You'll work across APIs, data models, integrations, and LLM orchestration, turning ambiguous product needs into reliable, scalable backend systems. You'll collaborate closely with product, frontend, and customer-facing teams, and you'll be trusted to make high-stakes engineering decisions with minimal oversight.

This role is ideal for engineers who combine deep technical skill with strong product intuition, enjoy mentoring others, and want to shape the technical direction of a fast-growing AI company.

What your first months could look like

Own the architecture of a new agent workflow end-to-end. Lead a design review that shapes how we integrate with a Fortune 100 HRIS. Ship an LLM orchestration improvement that measurably increases agent accuracy. Mentor a junior engineer through their first production deployment.

What You'll Do

Architecture & Systems

• Design and own the architecture of backend services that power Cascade's AI agent platform, making decisions on system boundaries, data flow, and scalability.

• Lead technical design for complex features — write design docs, drive architecture reviews, and ensure alignment across teams.

• Build and evolve APIs that support conversational interactions, task execution, and long-running enterprise workflows.

• Design data models and storage layers across relational and NoSQL databases (PostgreSQL, Firestore), optimizing for performance and reliability at scale.

• Own production reliability for your systems — define SLOs, build monitoring and alerting, and lead incident response.

AI/LLM Platform

• Develop and iterate on LLM orchestration logic in Python, including prompt execution, tool calling, state management, and evaluation frameworks.

• Build ingestion and retrieval pipelines for HR documents and structured data used by AI agents.

• Design and improve evaluation and testing frameworks to measure and increase agent accuracy and reliability.

Enterprise Integration & Security

• Integrate deeply with enterprise systems such as HRIS platforms (Workday, ADP, UKG), ticketing tools (ServiceNow, Jira), and communication tools (Slack, Microsoft Teams).

• Implement authentication, authorization, and access controls to meet enterprise security and compliance requirements.

Leadership & Collaboration

• Mentor junior and mid-level engineers through code reviews, pairing, and technical guidance.

• Identify and drive improvements to engineering processes, tooling, and best practices across the team.

• Collaborate with product, frontend, and customer teams to shape roadmap priorities and ship end-to-end features.
  

What You'll Need

Minimum Qualifications

• 5-8+ years of professional backend engineering experience in production environments.

• Strong proficiency in Python, including experience building backend services and data-intensive systems.

• Proven experience designing and building entire backend services end-to-end, with a track record of making sound architecture decisions.

• Solid understanding of data modeling and databases, including SQL (PostgreSQL) and NoSQL systems (e.g., Firestore or MongoDB).

• Experience with cloud infrastructure (GCP, Azure, or AWS), including service deployment, networking, and cost optimization.

• Familiarity with containerization and deployment workflows (Docker; Kubernetes strongly preferred).

• Strong software engineering fundamentals: system design, testing, performance, and reliability.

• Experience leading technical projects — scoping work, breaking down ambiguity, coordinating across teams, and delivering on time.

• Demonstrated ability to mentor other engineers and raise the quality bar for a team.

• Comfort operating with ambiguity and evolving requirements in a fast-paced environment.

Preferred Qualifications

• Experience building LLM-powered systems or AI-driven workflows in production.

• Familiarity with enterprise integrations (HRIS, ticketing systems, SSO via SAML/OIDC).

• Experience with background jobs, async processing, or event-driven architectures at scale.

• Knowledge of security best practices for handling sensitive employee data (SOC 2, GDPR).

• Experience operating and debugging production systems using observability tools (logs, metrics, traces).

• Prior experience at a startup or high-growth company, ideally in a technical leadership capacity.

• Experience contributing to or defining engineering standards, on-call processes, or platform tooling.

Who We're Looking For

• A backend engineer with deep technical expertise and the judgment to make architecture-level decisions independently.

• Someone who leads by example shipping high-quality code, raising standards, and helping others grow.

• Product-minded and focused on real customer impact, not just technical elegance.

• Pragmatic and detail-oriented, with a bias toward shipping and iterating.

• Curious about AI and motivated to make LLMs useful, reliable, and safe in real-world enterprise systems.

• Comfortable operating as a force multiplier unblocking teammates, driving alignment, and improving how the team works.