Senior Staff Software Engineer-Voice AI Agent Prompting

Job Description

The Forward Deployed Engineer, Voice AI Agent Engineering designs, builds, ships, and operates voice AI agents whose core behavior is model-driven rather than explicitly authored — conversational and agentic experiences that interpret caller intent over a live audio channel, reason over context, invoke tools, and act on the caller’s behalf. The engineer works across the full lifecycle: shaping ambiguous call flows and telephony requirements into precise specifications, authoring the instructions and prompts that govern voice agent behavior, proving through automated evaluation that the result behaves correctly on real calls. This is not a machine learning or AI research role — the engineer does not train foundation or speech models — but it is distinct from traditional software engineering, where systems follow deterministic call-flow logic rather than selecting execution paths at runtime.

Two things follow, and voice makes both harder. First, the agent’s most important logic often lives in natural language — instructions, prompts, tool descriptions, and guardrails — which must be engineered, versioned, and reviewed with the same discipline as code, while also holding up under what a spoken channel adds: turn-taking, barge-in, and disambiguating what speech recognition got wrong. Second, because behavior is probabilistic and happens live on a call, correctness is established by measuring behavior at scale — including latency, containment, and transcription accuracy — rather than by asserting fixed outputs, making automated evaluation a first-class engineering activity rather than a quality-assurance afterthought. The engineer owns the correctness of what ships to a live caller, whether a human or an agent produced it.

What You Get to Do in This Role

• Build voice AI agents. Design and ship agentic voice applications — intent interpretation, multi-step reasoning, tool invocation, and action on the caller’s behalf — together with the CTI, CCaaS, and telephony integrations that make them usable in production.

• Design AI-driven autonomous voice workflows. Decompose call flows and business processes into the steps and decision points a voice agent can execute — determining where autonomy is appropriate, where a live-agent handoff is required, and how misrecognition, retries, and escalation are handled.

• Engineer for what voice demands. Build experiences that hold context across turns, manage barge-in and interruption, recover gracefully from speech-recognition error, disambiguate caller intent, and confirm before consequential actions — all within the latency budget a live call imposes.

• Author and maintain voice agent instructions. Write, structure, and version the system instructions, role definitions, tool descriptions, guardrails, and escalation rules that govern voice agent behavior — as engineering artifacts under review and regression coverage, not configuration text.

• Engineer prompts for reliability rather than demo quality. Iterate prompts against measured call outcomes: task decomposition, golden call transcripts, structured output schemas, grounding and citation, graceful hand-back to a human agent, and the token and latency cost that directly shapes caller experience.

• Build automated evaluation and test non-deterministic voice behavior. Design and operate the evaluation that makes change safe on a live channel — golden call datasets, multi-turn conversation suites, model-as-judge scoring calibrated to human QA review, CI gates, and drift detection — plus adversarial, jailbreak, grounding, and tool-selection testing specific to voice.

• Specify precisely and direct AI coding agents. Convert customer call-flow and telephony requirements into testable specifications with explicit scope, constraints, and acceptance criteria; decompose work into agent-sized tasks; and review agent output for correctness and maintainability. You own the result regardless of what produced it.

• Deliver as a forward deployed engineer, embedded in the voice stack. Work directly inside a customer’s telephony, CTI, and CCaaS environment — building against their call data, integrations, and channels, tuning instructions and evaluation sets against live traffic, and returning with evidence that improves the product.

• Own quality, safety, and reliability on live calls. Monitor call containment, hallucination, unsafe actions, and transcription accuracy; defend against prompt injection and data leakage on live calls; and feed production call failures back into specifications and evaluation sets.

• Collaborate across product, design, and engineering. Partner with product managers, designers and platform teams to define success criteria, align on tradeoffs, and communicate capability and risk clearly

To Be Successful in This Role

A demonstrated track record of building, shipping, and operating production voice applications, including hands-on delivery of AI-native voice agent features that real callers depend on rather than demos. Direct experience authoring agentic instructions and prompts for voice, designing AI-driven autonomous call workflows, and building the evaluation and testing that verifies them against live call traffic, is required. Willingness to work directly with customers in a forward deployed capacity, embedded in their voice and contact center environment, is required. At least 10 years of experience in software engineering with at least 2 years of experience in deploying contemporary AI solutions at customers.

Education:Bachelor’s degree in Computer Science, Software Engineering, or a related technical field, or equivalent practical experience. Advanced degrees or certifications are a plus but are not a substitute for a demonstrated record of shipping reliable, production voice AI agents.

Key Competencies, Skills, and Experience

• Software engineering fundamentals. Strong command of data structures, algorithms, system design, APIs, data modeling, and testing.

• AI native voice application development. Hands-on experience building applications where model-driven behavior is central — agent orchestration at the application layer, tool and function calling, context assembly, grounding against enterprise data, and handling the latency, cost, and failure modes unique to a live audio channel.

• AI-driven autonomous workflow design. Demonstrated experience designing workflows in which voice agents carry out multi-step call processes with limited supervision: call-flow decomposition, decision points and autonomy boundaries, human-in-the-loop checkpoints, exception and retry handling, and observability over what the agent did and why.

• Voice and telephony platform expertise. Practical experience with telephony integration, speech recognition and synthesis, and streaming audio — including the barge-in, turn-taking, and confirmation patterns a live call requires.

• Agentic instruction authoring. Demonstrated skill writing and maintaining the natural-language logic that governs voice agent behavior — instructions, role definitions, tool descriptions, guardrails, and refusal and escalation rules — with versioning, review, and regression coverage applied as they would be to code.

• Prompt engineering. Intent-driven prompt design tuned for voice: decomposition, golden and few-shot examples, structured output and schema enforcement, grounding and citation, and disciplined iteration against call-level evaluation results rather than impressions.

• Evaluation and testing of non-deterministic voice systems. Ability to build measurable frameworks assessing call quality, agent behavior, tool-selection accuracy, and regression risk — golden call datasets, scenario suites, model-as-judge scoring with human QA calibration, continuous evaluation pipelines, and drift detection — plus adversarial, jailbreak, and grounding testing.

• Specification precision and architectural judgment. Ability to define call-flow problems rigorously enough that another engineer or an AI agent implements them correctly, and to decide soundly when to solve a problem in code, in instructions, or by delegating to an agent.

• Safety, security, and data handling. Working knowledge of risks specific to AI-integrated voice applications — prompt injection, sensitive-data and call-recording leakage, over-broad tool access, unsafe autonomous action — translated into concrete guardrails, least-privilege controls, and monitoring.

• Forward deployed delivery and stakeholder communication. Comfort working directly with customers inside their telephony environment under incomplete information and fixed timelines, judgment about when a fast local solution is right and when to hold out for the durable one, and credibility communicating capability, limitation, and risk to non-engineers.

Desired Experience

• Forward deployed or customer-embedded delivery. Prior work as a forward deployed engineer, solution engineer, or in professional services, delivering software inside a customer’s environment.

• Voice and contact center technology. Telephony and contact center platforms, IVR, speech recognition and synthesis, streaming audio, and real-time latency optimization.

• Conversation design partnership. Experience working alongside conversation or content designers, contributing to dialogue flow, tone, and error-recovery design.

• Evaluation and observability tooling. Evaluation frameworks, prompt and instruction management tooling, tracing for LLM applications, and analysis of production call transcripts at scale.

• Enterprise domain depth. Customer service, contact center operations, sales, or enterprise workflow, at a depth sufficient to challenge a requirement rather than only implement it.

• Years of Experience. At least 10 years of experience in software engineering with at least 2 years of experience in deploying contemporary AI solutions at customers

For positions in this location, we offer a base pay of $190,900 – $334,100, plus equity (when applicable), variable/incentive compensation and benefits. Sales positions generally offer a competitive On Target Earnings (OTE) incentive compensation structure. Please note that the base pay shown is a guideline, and individual total compensation will vary based on factors such as qualifications, skill level, competencies, and work location. We also offer health plans, including flexible spending accounts, a 401(k) Plan with company match, ESPP, matching donations, a flexible time away plan and family leave programs. Compensation is based on the geographic location in which the role is located and is subject to change based on work location.

Work Personas

We approach our distributed world of work with flexibility and trust. Work personas (flexible, remote, or required in office) are categories that are assigned to ServiceNow employees depending on the nature of their work and their assigned work location. Learn more here. To determine eligibility for a work persona, ServiceNow may confirm the distance between your primary residence and the closest ServiceNow office using a third-party service.

Equal Opportunity Employer

ServiceNow is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, national origin, age, disability, gender identity, veteran status, or any other category protected by law. In addition, all qualified applicants with arrest or conviction records will be considered for employment in accordance with legal requirements.

Accommodations

We strive to create an accessible and inclusive experience for all candidates. If you require a reasonable accommodation to complete any part of the application process, or are unable to use this online application and need an alternative method to apply, please contact [email protected] for assistance.

Export Control Regulations

For positions requiring access to controlled technology subject to export control regulations, including the U.S. Export Administration Regulations (EAR), ServiceNow may be required to obtain export control approval from government authorities for certain individuals. All employment is contingent upon ServiceNow obtaining any export license or other approval that may be required by relevant export control authorities.

From Fortune. ©2026 Fortune Media IP Limited. All rights reserved. Used under license.