Backend Engineer, API Team

Ovii's Interpretation of the Role

Sarvam is hiring a Backend Engineer for its API team to build high‑performance, cloud‑agnostic Python APIs that serve AI/ML models at scale. The role involves designing low‑latency, fault‑tolerant services, integrating data stores and streaming platforms, and ensuring secure, observable production deployments.

Role Snapshot

• Build low‑latency Python APIs for ML inference
• Design fault‑tolerant, cloud‑agnostic backend services
• Implement authentication, rate limiting, and security
• Integrate PostgreSQL, Redis, ClickHouse, and streaming
• Collaborate on CI/CD, canary releases, and observability

Must-Have Requirements

• Python
• FastAPI/Django/Flask (Python web frameworks)
• HTTP/WebSockets/gRPC protocols
• Low‑latency distributed backend design
• PostgreSQL/Redis/ClickHouse
• Docker
• Kubernetes
• CI/CD pipelines
• Authentication & authorization security
• At least one major cloud platform (Azure preferred)
• building low‑latency distributed backend systems
• Python API development for ML models
• cloud‑agnostic infrastructure

Nice-to-Have Signals

• Canary deployments / progressive rollouts
• Observability tools (Prometheus, Grafana, OpenTelemetry)
• Prior ML inference serving experience
• Open‑source contributions / GitHub portfolio
• Kafka or Redis Streams (familiarity)
• ML inference serving
• canary or progressive rollouts
• observability and monitoring

Work Setup

• Location: Bengaluru, India
• Work mode: ONSITE
• Employment type: Full-Time

Not Specified in JD

• Visa sponsorship
• Salary range
• Remote eligibility
• Education requirement
• Relocation
• Notice period

What You'll Likely Work On

• Design, develop and optimise Python‑based APIs for serving ML models at scale
• Build communication layers using HTTP, WebSockets, and gRPC
• Architect low‑latency, fault‑tolerant, secure backend systems for real‑time inference
• Implement authentication, rate limiting, prioritisation, and secure coding practices
• Integrate voice‑agent, LLM, and other AI SDKs
• Manage data storage and performance with PostgreSQL, Redis, and ClickHouse
• Create event‑driven streaming pipelines using Kafka or Redis Streams
• Support canary deployments, feature rollouts, and CI/CD pipelines
• Ensure observability, reliability, and vendor‑agnostic operation across Azure, AWS, GCP, and on‑prem

Good Fit If You Have

• Prior experience with ML model serving or inference infrastructure
• Familiarity with canary or progressive rollout techniques
• Experience using observability tools such as Prometheus, Grafana, or OpenTelemetry
• Contributions to open‑source backend projects or a strong GitHub portfolio
• Hands‑on work with Azure (preferred) or other cloud platforms