Agent Engineer at Sarvam AI (Bengaluru)

Job Description

Sarvam AI is hiring Agent Engineers in Bengaluru to build, test and run AI agents that go live at large Indian banks, insurers, NBFCs and government departments, handling millions of real interactions. The company is hiring across levels, from 3+ years of experience.

At a glance

• Role: Agent Engineer (hiring across levels)
• Location: Bengaluru
• Experience: 3+ years
• Focus: production AI agents, evaluations and system integrations
• Apply: open until filled (re-checked 12 October 2026)

What you will do

• Build production agents on Sarvam’s own stack, covering prompts, system design, workflows, tool integrations and evaluations
• Map the scenarios an agent must handle and decide how each should be treated, so coverage is designed rather than discovered in production
• Build fast proofs of concept when a customer wants to see results before committing at scale
• Integrate agents with core banking, CRM, ticketing, telephony and other client systems
• Own quality end to end: define what good looks like, build the evals that measure it and close the gap
• Tune for accuracy, cost, reliability and performance under real load, and instrument systems so drift is visible
• At senior levels, own the build playbooks and technical quality bar for a product area and bring partner engineers up to it

Sarvam’s posting stresses that the hard part is not the first demo but everything after it: covering the full range of situations an agent must handle, engineering for failure rather than the happy path, and treating agents as versioned, reviewed code held to a regression suite, so that quality does not quietly decay over time.

What Sarvam AI is looking for

• 3+ years of experience, with a record of shipping to production and keeping systems running afterwards
• Serious experience with LLMs and agents: context engineering, tool use, structured outputs, memory and the failure modes that appear at scale, using agentic frameworks with open and closed models
• Engineering discipline applied to AI: versions, tests, regressions and reproducibility
• The ability to define metrics that matter, build evaluation pipelines and tell real signal from noise
• Strong Python and range across backend services, data pipelines, APIs and cloud infrastructure
• Comfort working directly with a customer’s engineering team

Pay and location

Sarvam’s posting does not state a salary. The role is based in Bengaluru.

How to apply

Apply through the official Sarvam AI job posting. Sarvam AI’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 12 October 2026. Check the posting for location and work-authorisation details before you apply.

See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.