Backend Engineer - Studio Media Platform
Sarvam AI
Bengaluru, IndiaremotePosted 3 months ago
S
Skill Required
EngineeringBackend DeveloperPlatform EngineerQuery OptimizationObservabilityCD pipelinesR ProgrammingPostgreSQLKubernetesPrometheusWebSocketdesigningsimilar)buildingFastAPIPyTorchTestNGPythonDockerdesignRabbitMQAzureCI/CDCloudgRPCHelmAPIsFulltime
Key highlights
- 4–6 years of backend engineering experience required
- Strong Python and FastAPI proficiency (non-negotiable)
- Work on AI-first problems with population-scale impact
- High ownership and impact from day one
- Partnerships with leading Indian brands (Tata Capital, SBI Life, etc.)
- Backed by Lightspeed, Peak XV, and Khosla Ventures
Role overview
Sarvam is building India’s full-stack sovereign AI platform, focusing on making AI work for India across research, models, infrastructure, and applications. The company partners with leading enterprises and public institutions and is backed by top-tier investors like Lightspeed, Peak XV, and Khosla Ventures. This role involves working as a Backend Engineer on Sarvam’s Studio media platform, which includes AI dubbing, live translation, and shared services like voice cloning, stem separation, lip sync, and music generation. The engineer will build and maintain production services, ML pipeline libraries, and platform SDKs to enable multilingual media processing at scale for enterprise customers and Sarvam Studio users.
Responsibilities
- Design and optimize production FastAPI services for dubbing and live translation — multi-stage task orchestration, rate-limited scheduling, and backpressure controls for concurrent workloads
- Build and maintain distributed worker architectures with independent scaling per pipeline stage and automatic recovery of stuck or failed tasks
- Own the data layer — async ORM models, schema migrations, and query optimization on PostgreSQL
- Implement real-time features — WebSocket-based job tracking for dubbing and streaming audio pipelines for live translation
- Manage Kubernetes deployments — Helm charts, secrets management, ingress configuration, and multi-role container images
- Extend and maintain the core dubbing library across all pipeline stages: audio extraction, VAD, speech recognition, translation, QC, TTS, and final video stitching
- Integrate and optimize ML model serving — remote inference server clients and local model inference for audio analysis and vocal separation
- Build and improve QC orchestration — automated scoring, tempo analysis, guided normalization, and pronunciation verification
- Design async-first pipelines with efficient concurrency patterns for CPU-bound audio processing
- Maintain and evolve LLM integration layers for translation, QC, and pre-processing across multiple provider backends
- Build and maintain the shared Studio service SDK — reusable FastAPI middleware and routers for authentication, billing, workspace isolation, and input validation
- Design media storage abstractions — upload, signed URL generation, retention policies, and cloud blob storage integration
- Implement cross-cutting concerns: rate limiting, metering, audit trails, and request history across all Studio services
- Build observability foundations — OpenTelemetry instrumentation, structured logging, and metrics collection shared across services
- Maintain high test coverage with strong CI gates, parallel test execution, and thorough mocking of external services
- Instrument services with custom metrics and structured error tracking for production observability
- Manage CI/CD pipelines — automated testing, linting, container builds, artifact publishing, and version management
Requirements
- 4–6 years of experience in backend engineering, with a focus on building and operating production services at scale
- Strong proficiency in Python with hands-on experience building production FastAPI or similar async web services (non-negotiable)
- Deep understanding of async programming — asyncio, concurrent execution patterns, and designing for high-throughput workloads
- Experience with distributed task systems: task queues (Celery or similar), message brokers, and designing fault-tolerant job orchestration
- Hands-on with PostgreSQL and an async ORM (SQLAlchemy preferred) — comfortable with query optimization, schema design, and migrations
- Familiarity with audio/media processing: FFmpeg, common audio formats, and processing libraries like soundfile or librosa
- Experience integrating ML models into production — API-based (REST/gRPC) or local inference (PyTorch, ONNX Runtime)
- Experience building reusable libraries or SDKs — designing clean APIs, managing backward compatibility, and publishing packages for internal consumers
- Proficiency with Docker, Kubernetes, Helm charts, and at least one major cloud platform (Azure/GCP/AWS)
- Strong testing discipline — writing thorough tests, mocking external services, and maintaining CI/CD pipelines
Nice to have
- Prior experience with speech/NLP systems: ASR, TTS, or machine translation
- Experience with ML model serving infrastructure (Triton, TorchServe, or similar)
- Familiarity with LLM orchestration for structured output and multi-step agent workflows
- Experience with real-time streaming — WebSocket, WebRTC, or Server-Sent Events in production
- Familiarity with Indic languages and the nuances of multilingual content (code-mixing, transliteration, regional dialects)
- Experience designing platform middleware — auth, billing, rate limiting, or multi-tenant isolation
- Experience with observability tooling — Prometheus, Grafana, OpenTelemetry, or similar stacks
- Familiarity with video processing pipelines and media localization workflows
- Contributions to open-source backend, audio, or NLP projects
Benefits
- 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
- Work on problems that could change how an entire country learns, works, and communicates
Additional details
- The work cuts across multiple codebases: a core ML pipeline library (ASR, translation, TTS, audio processing), production services for dubbing and live translation, and a shared platform SDK that provides common capabilities to every Studio service.
- Sarvam partners with India’s leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC.
- 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.
- If you want to work on problems at the frontier of AI in India, Sarvam is the place to be.