SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Sarvam AI is building India's full-stack sovereign AI platform, backed by Lightspeed, Peak XV, and Khosla Ventures. The company partners with leading Indian enterprises and public institutions including Tata Capital, SBI Life, CRED, IDFC, and LIC.
Samvaad is Sarvam's conversational AI platform for enterprises, startups, and governments. You will own the end-to-end backend system that powers millions of voice calls daily, enabling customers to build, configure, deploy, and operate voice agents and campaigns at scale.
In this Staff Engineer role, you will be a hands-on technical owner with full IC scope and authority—no people management. Your responsibilities include:
- Design and own the complete backend for agent, campaign, and user management, from data modeling through API design to deployment, using Python and FastAPI
- Implement workflow orchestration with Temporal for complex, long-running, stateful operations
- Ensure performance and reliability for a multi-tenant SaaS platform operating at sub-second latency SLOs
- Build comprehensive observability (logging, metrics, tracing) to enable confident and rapid production debugging
- Develop integration testing infrastructure that allows fast shipping without breaking customer-facing systems
- Collaborate closely with the frontend team (Next.js) to deliver an experience worthy of the platform
- Establish a design-first and documentation-first engineering culture—RFCs before code, decisions documented, no tribal knowledge
You will set technical standards, make architectural trade-offs, and operate systems in production. This is a role for someone who thrives with ambiguous problems and takes them through to reliable, scalable production systems.
REQUIREMENTS:
- 8–12 years building production backend systems with deep expertise in Python and FastAPI (or Golang)
- Track record of full-stack ownership: designing systems end-to-end, making trade-offs, and operating them in production
- Hands-on experience with workflow orchestration at scale, ideally Temporal
- Experience building and operating high-scale distributed systems—multi-tenant, low-latency, resilient under real load
- Strong PostgreSQL and Redis fundamentals: schema design, query performance, caching strategy
- Sound judgment on build vs. buy, optimize vs. ship, abstract vs. inline decisions
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 with comfort for ambiguity, speed, and ownership
