As a Senior Engineer, AI, you will design, build, and deliver enterprise-grade AI solutions in close partnership with FDEs and cross-functional teams. This is a hands-on engineering role responsible for translating business requirements and architectural direction into scalable, secure, and maintainable AI systems.

We pride ourselves on encouraging a culture of innovation, agile ways of working, and transparency in all we do. Join us in embodying the spirit of the Un-carrier and make a tangible impact!

What You'll Do:

- Design and develop RAG pipelines, agentic workflows, and multi-model orchestration that solve high-value, domain-specific use cases across lines of business.

- Build and optimize the APIs, services, and integration layers that connect AI capabilities to enterprise data and systems.

- Partner with US-based FDEs to turn prioritized, ROI-driven opportunities into production-ready builds.

- Implement agentic AI systems that improve reasoning, tool use, and interaction across complex, multi-step workflows, working within defined architectural patterns and reference implementations.

- Contribute to and utilize CI/CD pipelines (GitLab or equivalent) to enable automated build, test, and deployment workflows.

- Implement instrumentation, structured logging, and tracing to monitor AI system performance, cost, and output quality, in partnership with platform and SRE teams.

- Leverage AI-assisted development tools to improve code quality, accelerate development, and enhance debugging.

- Contribute design input within defined architectural frameworks and evaluate trade-offs at the component or feature level.

- Collaborate with product, architecture, and engineering partners to translate business requirements into scalable technical solutions.

- Apply and help uphold AI engineering standards for performance, security, reliability, and compliance across deployed solutions.

What You'll Bring:

- 8+ years of professional software development experience, including hands-on experience building AI/ML or LLM-based systems.

- Experience designing and building RAG pipelines, agentic workflows, or multi-model orchestration.

- Experience developing backend services, REST APIs, and enterprise integration solutions using modern languages and frameworks.

- Experience with cloud platforms (AWS/Azure/GCP) and cloud-native application development.

- Experience integrating LLMs and agent frameworks with enterprise data and tooling, including connector/tool-use patterns (e.g., MCP) and retrieval and grounding strategies.

- Experience building and operating CI/CD pipelines (GitLab or equivalent).

- Experience incorporating observability into software solutions, including monitoring of AI system performance, cost, and output quality.

- Understanding of secure application design (authentication/authorization patterns, secrets handling).

- Ability to operate effectively in environments with evolving requirements.

- Strong ownership mindset and clear technical communication skills.

- Experience using AI-assisted development tools to improve productivity and engineering outcomes.

Must Have Skills :

- Hands-on experience building AI systems using LLMs - RAG, agentic workflows, or multi-model orchestration.

- Experience with cloud platforms (AWS/Azure/GCP) and cloud-native development.

- Experience developing backend services, REST APIs, and integration layers that connect AI capabilities to enterprise systems.

- Experience with agent and tool-use frameworks, including connector patterns (e.g., MCP).

Nice-to-Have :

- Experience designing high-throughput, low-latency distributed systems.

- Experience with prompt engineering and LLM evaluation frameworks.

- Experience with AI observability - output evaluation, hallucination detection, or agent tracing.

- Familiarity with frontend technologies (e.g., React) for building end-user AI experiences.

- Experience leveraging AI for log analysis, anomaly detection, or operational insights.

- Experience working in a forward-deployed, consulting, or customer-facing engineering model.

- Experience delivering solutions across multiple lines of business or domains, matching engineering effort to business value.