Job
Description
As a Backend Engineer in the API Team at Sarvam.ai, you will play a crucial role in building the API backbone that powers the next generation of AI systems for India and beyond. You will be responsible for designing, developing, and optimizing Python-based APIs for serving a family of ML models such as ASR, TTS, LLM, Vision models, and more at scale. Your work will involve collaborating on various aspects like building communication layers using HTTP, WebSockets, and gRPC, architecting low-latency and fault-tolerant backend systems, and managing integrations with voice agent SDKs and LLM SDKs. **Key Responsibilities:** - Design, develop, and optimize Python-based APIs (FastAPI, Django, Flask, or similar) for serving ML models at scale. - Work with HTTP, WebSockets, and gRPC to build robust communication layers. - Architect low-latency, fault-tolerant, and secure backend systems for real-time inference workloads. - Implement authentication, rate limiting, prioritization, and secure coding practices. - Develop and manage integrations with voice agent SDKs, LLM SDKs, and related AI interfaces. - Work with PostgreSQL, Redis, and ClickHouse for data management and performance optimization. - Build event-driven and streaming architectures using Kafka and Redis Streams. - Collaborate on canary deployments, feature rollouts, and CI/CD pipelines for smooth production releases. - Ensure systems are observable, reliable, and vendor-agnostic across multiple cloud environments. **Must-Have Skills:** - Strong proficiency in Python and experience with FastAPI, Django, Flask, or similar frameworks. - Deep understanding of HTTP, WebSockets, and gRPC protocols. - Proven experience building low-latency, distributed backend systems. - Hands-on experience with PostgreSQL, Redis, ClickHouse, or related data systems. - Familiarity with Kafka or Redis Streams for message handling. - Solid understanding of API authentication, authorization, and security best practices. - Experience with Docker, Kubernetes, and CI/CD pipelines. - Hands-on experience with any major cloud platform (Azure preferred but not mandatory). - Strong focus on secure coding practices and system reliability. **Good to Have:** - Experience with canary deployments, progressive rollouts, or feature flag systems. - Prior work with ML inference systems or AI model serving infrastructure. - Familiarity with observability and monitoring tools (Prometheus, Grafana, OpenTelemetry). - Contributions to open-source backend projects or a solid GitHub portfolio.,
