Intern — Backend Engineering (Dubbing Pipeline)
Sarvam AI
Software Engineering
Bengaluru, Karnataka, India
Location
Bengaluru
Employment Type
Full time
Location Type
On-site
Department
Engineering
About Sarvam
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.
About the Role
You’ll work directly on Sarvam’s production dubbing pipeline — a Python library and FastAPI service that orchestrates translation, text-to-speech, quality control, and audio stitching across 10+ Indian languages. This is backend software engineering: reading and improving real production code, adding features, handling failures gracefully, and making complex async systems reliable and fast.
Your code will run in production, processing real dubbing jobs. The emphasis is on clean architecture, robust error handling, and making the system easy to extend as new providers and capabilities are added.
What You’ll Do
Read, understand, and improve existing production Python code (async pipelines, API integrations, retry logic)
Add features: configurable parameters, structured logging, caching, timeout handling
Improve error handling: distinguish rate limits from auth errors from server failures, add fallback logic
Refactor for clarity and extensibility: provider abstractions, config objects, cleaner interfaces
Write code that integrates with external APIs (Gemini, ElevenLabs, Sarvam services) with proper retry and observability
What We're Looking For
Strong Python fundamentals — comfortable reading and writing production-quality code (not just notebooks)
Understanding of async/await and why it matters for I/O-bound services
Good instincts around error handling, logging, and making systems observable
Ability to read unfamiliar code quickly and trace data flow through a system
Familiarity with using AI coding tools (ChatGPT, Copilot, Claude) to accelerate your work
Bonus Points
Experience with FastAPI, aiohttp, or similar async Python frameworks
Familiarity with retry libraries (tenacity) or resilience patterns
Exposure to Pydantic, dataclasses, or typed Python
Experience writing tests and mocking external services
Understanding of API design and provider abstraction patterns
Why Sarvam?
Sarvam is a fast-moving, high talent-density team building full-stack AI for India, working on problems that push the frontiers of AI with real population-scale impact.
Work alongside researchers, engineers, builders, and business leaders who move fast and hold each other to a very high bar
High ownership and high impact, from day one
Everything we do is AI-first, from the way we build and ship to the way we think about problems
You can work on problems that could change how an entire country learns, works, and communicates
If you want to work on problems at the frontier of AI in India, Sarvam is the place to be.