ServiceNow: Senior Research Scientist, Agent Evaluation — Hyderabad, Telangana, India

About ServiceNow

ServiceNow develops an enterprise software platform bringing together data, workflows and AI for business operations. Its employer introduction traces the business to automating a repetitive workplace task and describes a continuing focus on freeing people from routine work. The platform is intended to connect technology with how organisations carry out their processes. This makes workflow automation and the use of information in everyday business activity central themes, rather than a product aimed at only one industry.

The position and its setting

ServiceNow lists Senior Research Scientist, Agent Evaluation in Hyderabad, Telangana, India, under reference JB0075773. The details below separate the work described by the employer from essential conditions, preferred experience and practical preparation advice.

• Department: Engineering, Infrastructure and Operations
• Employment type: Full-time
• Employer listing date: 29 September 2026
• Brands: ServiceNow

Responsibilities and work described

• We build the evaluation layer that validates AI agents before they reach customers — an automated system that scores across large volumes of agent traces
• You'll own core parts of that platform: the pipeline that runs traces through model-based judges at scale, and the scoring logic that turns raw output into results teams can act on
• Design: evaluation methodologies and benchmarks for agent reasoning, planning, tool use, reliability, and safety — across LLM-as-a-Judge, trajectory-based, and human evaluation
• Take problems from research question to prototype to shipped feature, owning them end to end
• Building: and harden the pipelines and scoring logic behind customer-facing evaluation
• Curate synthetic and real-world datasets; measure the evaluator itself for consistency and agreement with human labels

Essential requirements and candidate background

• 5+ years in ML, applied AI, prompt engineering, agentic AI, including shipping something real to users
• Python skills
• Practical depth in agentic AI and context engineering: planning, reasoning, memory, tool use, retrieval, long-context
• Experience designing evaluation methodologies, not just running evaluations
• Hands-on production work with LLM APIs — prompt engineering, structured output, cost and latency tradeoffs
• Clear communication with technical and non-technical audiences
• Good to have Experience with AI-assisted development tools (Claude code, Windsurf, or similar)

Location, schedule and contract conditions

• Work arrangement: Hybrid
• Advertised location: Hyderabad, Telangana, India

Employer details to confirm

• The employer’s seniority category and its stated experience requirements do not agree. Follow the role-specific requirements above rather than assuming this is a fresher opening.

Pay and application dates

A verified salary figure is not established in this article. An online estimate for another Senior Research Scientist, Agent Evaluation vacancy is not an offer for reference JB0075773; use the employer’s own pay disclosure and recruitment communication.

A closing date is not confirmed in this article. Check the current employer page before submitting: an undated posting can change or be withdrawn.

How to apply to ServiceNow

Applications follow the official employer page linked below.

Open the official ServiceNow posting below and match the title and reference JB0075773.

Compare your qualifications and experience with the essential conditions for the Hyderabad, Telangana, India position, then read the preferred criteria separately.

Prepare an accurate CV and the supporting items requested in that employer’s application. Provide only information and documents you are authorised to share.

Use the employer’s application option, complete the required fields and review the submission. Retain the acknowledgement when one is provided. Job Alerts World does not receive the application.

Practical preparation: Python

Python work is easier to assess through a concrete example than a list of libraries. Explain the problem, the input data, the parts you implemented and how you checked the output. Include a repository or a short technical note when you can share it.

Relevant skills

• Python
• APIs
• AI/ML
• LLMs
• AI
• communication