Sr Software Engineer

ServiceNow · Hyderabad, , India

  • Senior
  • Full-time
  • Posted 2026-10-29
  • Confirmed live on 10 November 2026

Apply at ServiceNow

Job description

Job Description
Overview
The AI Application Software Engineer designs, builds, ships, and operates applications whose core behavior is model-driven rather than explicitly authored — conversational and agentic experiences that interpret user intent, reason over context, invoke tools, and act on the user's behalf. In Field Service Management, this means building AI-native experiences for scheduling, dispatch, and service workflows that automate routine work, escalate exceptions, and improve customer outcomes.
This is a hands-on, forward deployed role for a senior engineer whose first instinct is AI — someone who can shape ambiguous customer problems into precise specifications, author the instructions and prompts that govern agent behavior, build the application and integrations around them, and prove through automated evaluation that the result behaves correctly. This is not a machine learning or AI research role; you will not train foundation models. You own what ships, whether a human or an agent produced it.
What You Get to Do
• Build AI-native applications. Design and ship applications built around agentic behavior across Field Service Management — scheduling, dispatch, and workflows that reason over context, automate routine work, and escalate exceptions.
• Work AI-first in delivery. Direct coding agents to build, refactor, and test; use AI to think more sharply in front of customers; and apply it as part of everyday engineering practice rather than as a side tool.
• Deliver forward deployed. Work embedded in customer environments, tuning instructions and evaluation sets on the ground, using AI to compress turnaround without cutting quality.
• Author and maintain agentic instructions. Write, structure, and version the system instructions, role definitions, tool descriptions, guardrails, and escalation rules that govern agent behavior — treating them as reviewed, regression-covered engineering artifacts.
• Build automated evaluation and test non-deterministic behavior. Design and operate golden datasets, multi-turn conversation suites, model-as-judge scoring, CI gates, drift detection, adversarial testing, and grounding checks that make change safe.
• Design conversational experiences. Build experiences that hold context, confirm before consequential actions, and hand off cleanly to humans.
• Collaborate across product, UX, and documentation. Bring the AI-first instinct into cross-functional partnerships, not just your own code.
• Own quality and safety in production. Monitor containment, hallucination, prompt injection, and data leakage, then feed failures back into specifications and evaluation sets.

Qualifications
Experience

A demonstrated track record of building, shipping, and operating production software, including hands-on delivery of AI-native application features that real users depend on rather than demos. Direct experience authoring agentic instructions and prompts, designing AI-driven workflows, and building evaluation and testing for non-deterministic behavior is required. Experience with chat experiences is required; voice or multi-channel experience is strongly preferred. Willingness to work directly with customers in a forward deployed capacity is required; prior forward deployed experience is an advantage.
Education

Typically requires a minimum of 5 years of related experience with a Bachelor's degree; or 3 years and a Master's degree; or a PhD without experience; or equivalent work experience.
Key competencies

• Software engineering fundamentals. Strong command of data structures, algorithms, system design, APIs, data modeling, and testing. Good to have technologies like HTML, CSS, JavaScript and Java.
• AI-native application development. Hands-on experience with agent orchestration at the application layer, tool and function calling, context assembly, grounding against enterprise data, and handling latency, cost, and failure.

• Agentic instruction and prompt engineering. Demonstrated skill with instructions, role definitions, tool descriptions, guardrails, structured outputs, grounding, citation, graceful failure, and disciplined iteration against measured outcomes.

• Specification precision. Ability to define a problem rigorously enough that another engineer or an AI agent implements it correctly, and to judge when to solve it in code, in instructions, or by delegating.

• Customer-facing delivery with AI-native speed. Comfort working directly with customers under real constraints, using AI to cut turnaround, and communicating capability and risk credibly to non-engineers.

• AI safety and data handling. Working knowledge of prompt injection, data leakage, over-broad tool access, and unsafe autonomous action, translated into concrete guardrails and least-privilege controls.
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 envir

Interview problems reported for ServiceNow

Reported by candidates and public write-ups, not by ServiceNow. Practice each one here:

More at ServiceNow

More like this

All open software jobs