It is everything after: mapping the full space of what an agent has to handle so the scenarios that matter are covered by design rather than discovered in production, engineering for the failure modes instead of the happy path, and building the evals and… We are hiring across levels, from 3+ years of experience.
Build production agents on the Sarvam stack: prompts, system design, workflows, tool integrations, and evals.
Map the space the agent has to cover. Work out the scenarios that matter, how each should be handled…
Build the proof of concept when a customer wants to see it work before committing at scale, and get to a convincing result fast.
Integrate into systems that were never designed for this: core banking, CRM, ticketing, telephony, and whatever else the customer runs.
What matters more than years is whether you have built something real users depended on and kept it working.
You have shipped to production and owned it afterwards. Not just built it. Kept it running, fixed it at 11pm…
You have worked with LLMs and agents seriously. Context engineering, tool use, structured outputs, memory…
You bring engineering discipline to AI. You think in versions, tests, regressions and reproducibility. You are uncomfortable when a system's behaviour depends on a…
Experience: Mid-level · 3+ years · Job type: Full-time
More open roles like this one
Bengaluru, KA, IndiaIndia & South Asia
Canberra, AUST CAPITAL TERR, AustraliaAsia-Pacific
Sydney, NSW, AustraliaAsia-Pacific
Agent Engineer · Sarvam AI
Don't have an account? Already have an account?