Digital Agent Developer

Description

The company is an impact-driven Fortune 10 business that works across almost every part of healthcare, known for insights, products and services that make care easier to reach and more affordable.

The Contact Center AI team uses AI and digital agents to improve the customer journey across voice, chat and email for the company's businesses. The team designs, builds and runs digital agents on Sierra Agent OS and connects them to the contact center and surrounding enterprise systems.

You will design, build, test and keep improving conversational AI agents that serve customers and business teams. You will work inside the Sierra Agent OS ecosystem, creating reusable agent patterns and raising performance through testing, analytics and tuning. You will work alongside platform engineers, solution architects and business stakeholders.

This is where new agents and capabilities get built and existing ones get better. Sierra is new, so Sierra experience is welcome but not required, and you will be trained on it. The team needs real experience building AI agents, including prompts, tool calling, handoffs and testing, plus the judgment to recognise when an agent is getting things wrong.

Responsibilities

• Design, configure and tune conversational AI agents in Sierra Agent OS.
• Create reusable reference models and design patterns that work for several business use cases.
• Build and improve agent experiences across voice, chat and email.
• Study conversation data and performance metrics to raise accuracy, containment and customer outcomes.
• Write and refine prompts, workflows, decision logic and handoff experiences.
• Work with platform engineers and solution architects on multi-LLM orchestration.
• Support testing, deployment, monitoring and ongoing improvement of AI agent solutions.
• Run simulations and regression tests before each release, then review production conversations where the agent failed, find the cause and fix it.
• Work with integration and platform teams on the APIs and tools agents call, such as account lookup, order status, case creation and appointment scheduling, and define how the agent should act when those calls fail.
• Keep agent documentation, test cases and the support runbooks used by the service desk and L3 support.
• Follow enterprise security, compliance, documentation and governance standards.

Requirements

• At least 2 years building AI agents or conversational AI, such as LLM-based assistants, chatbots or voicebots, or in AI/ML or software development with hands-on agent work.
• A bachelor's degree in Computer Science, Engineering, Information Technology, Data Science or equivalent experience.
• Hands-on experience designing, building or tuning LLM-based agents or digital assistants, covering prompts, tool and function calling, workflows, guardrails and handoff to human agents.
• Hands-on experience with prompt engineering, conversational design, intent modeling or Natural Language Understanding (NLU).
• Working knowledge of agentic AI patterns: multi-step tool use, retrieval (RAG), agent evaluation and testing, and the ways agents fail in production. This can come from any agent platform.
• Experience analysing data and using the findings to improve AI performance and user outcomes.
• Knowledge of APIs, JSON and modern software practices, with the ability to read API responses, logs and conversation transcripts to explain why an agent acted as it did.
• Familiarity with CI/CD pipelines, version control and testing methods.
• Strong problem-solving, communication and cross-functional collaboration skills.
• Preferred: experience with multi-agent systems, agent frameworks or SDKs such as LangGraph, OpenAI Agents SDK, Bedrock Agents or Vertex Agent Builder, or with MCP-based tool integration.
• Preferred: hands-on Sierra Agent OS experience, or work on other agent platforms such as Salesforce Agentforce, Google CCAI/Dialogflow, Amazon Lex/Connect, Kore.ai or Microsoft Copilot Studio.
• Preferred: hands-on work with voice AI, chatbots, virtual assistants or customer-service automation.
• Preferred: knowledge of multi-LLM routing, orchestration, retrieval-augmented generation (RAG) or AI evaluation frameworks.
• Preferred: experience in healthcare, regulated industries or enterprise-scale environments.
• Preferred: exposure to analytics and monitoring tools used to assess conversational AI performance.
• Preferred: experience testing conversational agents with simulation or automated tools, such as Tosca or custom test harnesses.
• Preferred: familiarity with systems a contact center agent typically connects to, such as Five9 or another CCaaS platform, Salesforce Service Cloud, SAP or MuleSoft APIs.
• Preferred: experience working with product, architecture, platform engineering and business teams.
• Preferred: familiarity with cloud-native application development and integration patterns.

Conditions

Travel is minimal and depends on business needs.

Work is hybrid or remote, subject to business and team requirements.

You must be able to work at a computer and join virtual and in-person meetings for long periods.

Equal opportunity employer.

Benefits

• Base pay range is $81,500 - $108,600.
• Pay is set by performance, experience and skills, equity, periodic job market reviews and geographic market, and always complies with applicable regulations.
• Other compensation, such as an annual bonus or long-term incentive opportunities, may be offered.
• Competitive compensation is part of the company's Total Rewards package, and more information on benefits is available.