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 enabling enterprises, startups, and governments to build, configure, deploy, and operate voice agents and campaigns at scale. The platform currently powers millions of voice calls daily with deep personalization and user understanding.
You will own the end-to-end backend system that powers agent, campaign, and user management for this multi-tenant SaaS platform. This is a hands-on individual contributor role with full scope and authority—no people management.
Key responsibilities:
- Design and implement the complete backend for agent, campaign, and user management using Python and FastAPI, from data modeling through API design to deployment
- Architect and maintain workflow orchestration using 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 infrastructure (logging, metrics, tracing) enabling 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 underlying platform
- Establish design-first and documentation-first engineering culture within your team through RFCs, written decisions, and elimination of tribal knowledge
Requirements:
- 8-12 years building production backend systems with deep expertise in Python and FastAPI (or Golang)
- Must-have: hands-on experience building telephony infrastructure, primarily SIP/VoIP
- Proven 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 with multi-tenant architecture, low-latency requirements, and resilience under real load
- Strong PostgreSQL and Redis fundamentals including schema design, query performance, and caching strategy
- Sound judgment on build vs. buy decisions, optimization vs. shipping, and abstraction vs. inlining
Nice to have:
- Experience building products on top of LLMs or AI/ML systems
- Time at an early- or growth-stage startup with comfort in ambiguity, speed, and ownership
