Sarvam is building the bedrock of Sovereign AI for India. The company is developing India's full-stack sovereign AI platform, building across research, models, infrastructure and applications with a singular focus on making AI genuinely work for India. Sarvam works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures. Sarvam partners with India's leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC.
At the heart of Sarvam's conversational AI platform sits the system that lets our customers build, configure, deploy, and operate voice agents and campaigns -- at scale. Today it handles 50M+ minutes of conversations every month, and it's growing fast.
We're looking for a Staff Engineer to own this system end-to-end. The data model. The APIs. The orchestration. The reliability. The performance. The standards we hold ourselves to. This is an IC role with the scope and authority of one -- no people management, just the systems and the bar.
What You'll Own
The end-to-end backend for agent, campaign, and user management -- from data modeling through API design to deployment, in Python and FastAPI
Workflow orchestration with Temporal for complex, long-running, stateful operations
Performance and reliability for a multi-tenant SaaS platform operating at sub-second latency SLOs
Observability -- logging, metrics, tracing -- so the team can debug production confidently and quickly
Integration testing -- the test infrastructure that lets us ship fast without breaking customer-facing systems
Close collaboration with the frontend team (Next.js) to deliver an experience worthy of the underlying platform
Setting the design-first and documentation-first engineering culture within your team -- RFCs before code, decisions written down, no tribal knowledge
What We're Looking For
5-10 years building production backend systems, with deep expertise in Python and FastAPI (or Golang)
A track record of full-stack ownership -- you've designed systems end-to-end, made the trade-offs, and operated them in production
Hands-on experience with workflow orchestration at scale, ideally Temporal
Built and operated high-scale distributed systems -- multi-tenant, low-latency, resilient under real load
Strong PostgreSQL and Redis fundamentals -- schema design, query performance, caching strategy
The judgment to know when to build vs. buy, when to optimize vs. ship, when to abstract vs. inline
Nice to Have
Experience building products on top of LLMs or AI/ML systems
Background in telephony, VoIP, or SIP infrastructure
Time at an early- or growth-stage startup -- comfort with ambiguity, speed, and ownership
Interested in this role?
We're always looking for curious minds who care deeply about building technology that matters.