Software Engineer - Model API Platform

The role

You will own and operate major parts of the model API platform, such as WebSocket streaming or speech pipelines. You will build real-time and model-serving pipelines while optimizing for low latency and reliability.

What you will do

• Own one or more major parts of the platform including building, operating and improving them.
• Turn loosely defined goals into RFCs, milestones and shipped results.
• Be accountable for on-call, incident response, root-cause analysis and fixes.
• Build and operate streaming infrastructure like WebSocket connections and queue-based batch processing.
• Engineer audio pipelines including TTS chunking, sample-rate conversion and VAD-based silence detection.
• Hold services to sub-100ms latency SLOs in a multi-tenant environment.
• Strengthen the integration testing harness.
• Partner with Inference and MLOps teams on model serving.
• Mentor junior engineers through RFC reviews, code review and pairing.
• Practice design-first, documentation-first engineering.

Required qualifications

• 4–6 years of building and operating production backend systems.
• At least one service owned end to end under real load.
• Strong distributed-systems fundamentals: concurrency, networking, queues, caching, consistency and failure modes.
• Experience with low-latency or high-throughput services.
• Solid fundamentals with a relational database and a cache, such as PostgreSQL and Redis.
• Fluency in at least one backend language.
• Willingness to work in both Python and Golang.
• Experience running services with containers, CI/CD and production monitoring.
• Daily, hands-on use of AI tools in your engineering workflow.
• Clear writing, especially RFCs and design docs.

Nice to have

• Voice AI or real-time audio experience: WebSockets, WebRTC, streaming ASR or TTS, or audio processing with FFmpeg or pyav, codecs, sample rates and VAD.
• Production experience in Go, or in Python with FastAPI.
• Experience serving LLM, ASR, TTS or vision models in production.
• Experience building metering, billing, wallet or payments infrastructure.
• Running services on Kubernetes in production.
• Time at an early- or growth-stage startup.

About the company

Sarvam is building the bedrock of Sovereign AI for India, developing a full-stack sovereign AI platform across research, models, infrastructure and applications. The company is backed by Lightspeed, Peak XV and Khosla Ventures.