Applied AI Engineer, Sarvam Agents

Sarvam is building India's full-stack sovereign AI platform (backed by Lightspeed, Peak XV, and Khosla Ventures) across speech, text, translation, and conversational agents. As an Applied AI Engineer on the Sarvam Agents team, you own production AI agents end-to-end.

Responsibilities:

• Build agents end-to-end: flow design, prompting, tool definitions, memory, evaluation, deployment.
• Own agent reliability in production: debugging real failures, designing guardrails.
• Manage the agent runtime, OAuth/SaaS integrations, MCP server infrastructure, memory systems, multi-tenancy, evaluation frameworks, and observability.

Requirements:

• 2+ years Python backend development.
• LLM API fluency: prompt design, structured outputs, function calling.
• RAG patterns: chunking, embeddings, hybrid search, reranking, vector databases.
• Experience with agentic frameworks (LangGraph, ADK, or equivalent).
• PostgreSQL/MySQL, Redis, production MCP server experience.
• Observability tools (Signoz, Datadog); eval frameworks (LangSmith, Braintrust) a bonus.