SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 190,900 - 334,100 / annual
ServiceNow is seeking a Senior Staff Software Engineer to design, build, ship, and operate voice AI agents whose behavior is model-driven rather than explicitly authored. This role bridges AI engineering and traditional software engineering, focusing on conversational and agentic experiences that interpret caller intent over live audio channels, reason over context, invoke tools, and act on the caller's behalf.
Key responsibilities include:
• Build production voice AI agents with intent interpretation, multi-step reasoning, tool invocation, and caller-behalf actions, integrated with CTI, CCaaS, and telephony systems.
• Design AI-driven autonomous voice workflows by decomposing call flows into executable steps, determining autonomy boundaries, and handling misrecognition, retries, and escalation.
• Engineer for voice-specific challenges: context management across turns, barge-in handling, speech-recognition error recovery, intent disambiguation, and confirmation within live-call latency budgets.
• Author and maintain voice agent instructions as engineering artifacts: system instructions, role definitions, tool descriptions, guardrails, and escalation rules under version control and regression coverage.
• Engineer prompts for reliability: iterate against measured call outcomes using task decomposition, golden transcripts, structured schemas, grounding, and token/latency optimization.
• Build automated evaluation frameworks for non-deterministic voice behavior: golden call datasets, multi-turn suites, model-as-judge scoring calibrated to human QA, CI gates, drift detection, and adversarial testing.
• Specify requirements precisely and direct AI coding agents: convert call-flow and telephony requirements into testable specifications; decompose work into agent-sized tasks; own correctness regardless of implementation source.
• Deliver as a forward-deployed engineer embedded in the customer's voice stack: build against their call data and integrations, tune instructions against live traffic, and return with evidence that improves the product.
• Own quality, safety, and reliability on live calls: monitor containment, hallucination, unsafe actions, and transcription accuracy; defend against prompt injection and data leakage; feed production failures into specifications and evaluation.
• Collaborate across product, design, and engineering to define success criteria, align on tradeoffs, and communicate capability and risk.
Requirements:
• Minimum 10 years of software engineering experience with at least 2 years deploying contemporary AI solutions at customers.
• Demonstrated track record building, shipping, and operating production voice applications with hands-on delivery of AI-native voice agent features (not demos).
• Direct experience authoring agentic instructions and prompts for voice, designing AI-driven autonomous call workflows, and building evaluation/testing against live call traffic.
• Willingness to work directly with customers in forward-deployed capacity, embedded in their voice and contact center environment.
• Bachelor's degree in Computer Science, Software Engineering, or related technical field (or equivalent practical experience).
• Strong software engineering fundamentals: data structures, algorithms, system design, APIs, data modeling, testing.
• Hands-on AI-native voice application development: agent orchestration, tool/function calling, context assembly, grounding, latency/cost/failure mode handling.
• Demonstrated AI-driven autonomous workflow design: call-flow decomposition, decision points, autonomy boundaries, human-in-the-loop checkpoints, exception handling, observability.
• Voice and telephony platform expertise: telephony integration, speech recognition/synthesis, streaming audio, barge-in, turn-taking, confirmation patterns.
• Agentic instruction authoring: writing and maintaining natural-language logic governing voice agent behavior with versioning, review, and regression coverage.
• Prompt engineering for voice: intent-driven design, decomposition, few-shot examples, structured output, grounding, citation, iteration against call-level evaluation.
• Evaluation and testing of non-deterministic voice systems: measurable frameworks for call quality, agent behavior, tool accuracy, regression risk, golden datasets, scenario suites, model-as-judge scoring, continuous pipelines, drift detection, adversarial/jailbreak/grounding testing.
• Specification precision and architectural judgment: define problems rigorously for correct implementation; decide when to solve in code, instructions, or via agent delegation.
• Safety, security, and data handling: knowledge of AI-integrated voice risks (prompt injection, data leakage, over-broad tool access, unsafe actions) translated into guardrails, least-privilege controls, monitoring.
• Forward-deployed delivery and stakeholder communication: comfort working directly with customers under incomplete information and fixed timelines; judgment on fast local vs. durable solutions; credibility communicating capability, limitation, and risk.
Desired experience: forward-deployed or customer-embedded delivery; voice and contact center technology; conversation design partnership; evaluation and observability tooling; enterprise domain depth (customer service, contact center, sales, workflow); advanced degrees or certifications.
