Staff Engineer - Systems Engineering

About this job

Sarvam AI is creating India's full-stack sovereign AI platform, focusing on research, models, infrastructure, and applications to make AI work for the country. The company partners with major public institutions and leading enterprises like Tata Capital, SBI Life, and CRED. As a Staff Engineer for Systems Engineering, you will join the team behind Samvaad, a conversational AI platform that powers millions of personalized voice calls daily. In this hands-on individual contributor role, you will take ambiguous challenges and build reliable production systems. A normal day involves owning the end-to-end backend architecture, designing APIs, managing workflow orchestration, ensuring sub-second latency performance, handling multi-tenant SaaS reliability, building integration test suites, and collaborating closely with the Next.js frontend team while establishing a strong documentation-first engineering culture through RFCs.

Responsibilities

• Own the end-to-end backend for agent, campaign, and user management using Python and FastAPI.
• Manage workflow orchestration for complex, long-running, and stateful operations using Temporal.
• Drive performance and reliability for a multi-tenant SaaS platform targeting sub-second latency SLOs.
• Set up comprehensive observability including logging, metrics, and tracing for rapid production debugging.
• Build integration test infrastructure to ship fast without breaking customer-facing systems.
• Partner closely with the Next.js frontend team to deliver a seamless user experience.
• Establish a design-first and documentation-first culture by writing RFCs and avoiding tribal knowledge.

Requirements

• 8 to 12 years of experience in building production backend systems.
• Deep expertise in Python and FastAPI, or Golang.
• Demonstrated track record of full-stack ownership of systems from design to production operation.
• Hands-on experience with workflow orchestration at scale, specifically using Temporal.
• Experience building and operating high-scale, resilient, multi-tenant distributed systems with low latency.
• Strong fundamental knowledge of PostgreSQL and Redis covering schema design, query performance, and caching.
• Sound technical judgment regarding when to build versus buy, optimize versus ship, and abstract versus inline.

Good to have

• Experience building products on top of LLMs or AI/ML systems.
• Background in telephony, VoIP, or SIP infrastructure.
• Previous experience at an early- or growth-stage startup with comfort in handling ambiguity and speed.

Who should apply

This role suits experienced backend engineers with 8 to 12 years of background in creating resilient, high-scale distributed systems. Candidates must possess deep expertise in Python, FastAPI, PostgreSQL, and Redis, along with familiarity using Temporal for workflow orchestration. If you thrive in an individual contributor capacity, excel at end-to-end technical ownership, and are comfortable navigating the ambiguity and speed of a growth-stage startup environment, you will find this position a great fit.

Frequently asked questions