Latest AI JobsBrowse Jobs
Sarvam AI logo

Staff Engineer, API Platform

Sarvam AIBengaluruEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Posted
21 May 2026
Status
Open · checked 7d ago

About this role

Sarvam AI is seeking a Staff Engineer for its API Platform in Bengaluru to lead the end-to-end design, reliability, and performance of foundational model APIs. This hands-on individual contributor role is ideal for an experienced backend specialist passionate about scaling critical AI infrastructure.

Role Overview

As the Staff Engineer for the API Platform, the professional will own the complete architecture that serves millions of daily API calls for Automatic Speech Recognition (ASR), Text-to-Speech (TTS), Vision, and Large Language Models (LLMs). Operating from the Bengaluru office, the role requires leading a major technology transition by migrating the existing Python and FastAPI platform to Go while maintaining strict latency and reliability standards.

Key Responsibilities

Own the end-to-end architecture and evolution of the platform from edge request to final response.
Lead the migration from Python to Go, establishing robust architectural patterns and ensuring zero drop in production reliability.
Engineer complex audio pipelines involving TTS chunking, sample-rate adjustments, format encoding, and VAD-based silence detection.
Manage vision pipelines by orchestrating OCR, layout detection, and VLM harnesses for structured data extraction.
Scale streaming infrastructure handling WebSocket connections, queue-based batch processing, backpressure, and low-latency model invocations.
Develop and maintain the commercial layer, incorporating metering, billing, prepaid wallet management, and rate-limiting.
Implement comprehensive observability systems covering logging, metrics, and tracing for rapid production debugging.
Partner closely with Inference and MLOps teams to mentor them on production-grade engineering practices.
Foster a design-first, documentation-first culture utilizing RFCs and written decision-making.

Requirements

Minimum of 7 years of professional experience building production backend systems at scale.
Proven production expertise designing, building, and operating Go services under heavy load.
Proficiency in Python, specifically working with the FastAPI foundation during the system rewrite.
Demonstrated track record in designing and operating high-scale, low-latency, multi-tenant distributed systems.
Hands-on background with real-time streaming systems, WebSockets, long-lived connections, and backpressure management.
Strong foundational knowledge of PostgreSQL and Redis, including schema design, query tuning, and caching strategies.
Practical experience operating production services on Kubernetes.
Senior individual contributor judgment balancing build versus buy, optimization versus speed, and abstraction versus inlining.

Nice to Have

Prior experience serving LLMs, ASR, TTS, or vision models in a production environment.
Background in audio processing utilizing tools like pyav, FFmpeg, codecs, sample-rate manipulation, or VAD.
Experience developing metering, billing, wallet systems, or payments infrastructure.
Previous tenure at an early or growth-stage startup demonstrating comfort with ambiguity and high ownership.

Skills and Tools

Go
Python
FastAPI
Kubernetes
PostgreSQL
Redis
WebSockets
FFmpeg
Distributed Systems

About the Company

Sarvam AI is building a full-stack sovereign AI platform for India, focusing on research, models, infrastructure, and applications tailored to the nation's needs. Backed by prominent investors like Lightspeed, PeakXV, and Khosla Ventures, the company partners with major Indian enterprises and public institutions including Tata Capital, SBI Life, CRED, IDFC, and LIC.

How to Apply

Interested candidates should visit the official Sarvam AI careers page to submit their application for the Staff Engineer, API Platform position.

Skills and tech stack

PythonKubernetesLLMMLOps

Questions candidates ask

What is the primary location for the Staff Engineer, API Platform role?

The position is based in Bengaluru, India.

What programming languages are used in this role?

The role utilizes both Python (specifically FastAPI) and Go, as the platform is currently undergoing a rewrite from Python to Go.

How many years of experience are required?

Candidates must have 7+ years of experience building production backend systems at scale.

Is this a management or individual contributor role?

This is a hands-on individual contributor (IC) staff engineer role.

What kind of traffic does the API platform handle?

The platform handles tens of millions of API calls every day across HTTP and WebSockets with sub-second latency SLOs.

Ready to apply?

The application is on the official Sarvam AI careers page.

Apply on company site