Sarvam
Technology
AppliedAIEngineer,SarvamAgents
Neural analysis suggests this role is
optimal for Mid candidates.
“Applied AI Engineer, Sarvam Agents at Sarvam. Skills: Applied AI, Agent development, Production systems, LLM APIs. Build agents end-to-end. Design agent flows”
Industry & Context.
Debugging; Troubleshooting; Root cause analysis
What They're Looking For.
Must Have
2+ years backend development, LLM API fluency, Agentic framework experience, Production MCP servers, Shipped AI features, RAG patterns, Building and running evals, Cost and latency optimization, Observability fluency, Integrating third-party APIs, PostgreSQL or MySQL, OAuth flows
Nice to Have
Open-source contributions, Eval frameworks familiarity, Human-in-the-loop design, Startup experience
What You'll Do.
Build agents end-to-end
Implement agent memory
Evaluate agent performance
Own agent reliability
Design agent guardrails
Run incident response
Implement scheduled triggers
Execute long-running agents
Build connector framework
Build MCP server infrastructure
Engineer memory and context
Implement multi-tenancy
Manage agent permissions
Implement audit trails
Develop eval infrastructure
Define tool error messages
Implement tool idempotency
Define tool retry semantics
Engineer streaming traffic
Engineer live agent cost
Engineer live agent latency
Implement observability
Perform integration testing
Manage prompt iteration
Implement prompt versioning
Run prompt A/B testing
Implement safe rollback
Full Job Description
About Sarvam Sarvam is building the bedrock of Sovereign AI for India. The company is developing India’s full-stack sovereign AI platform, building across research, models, infrastructure and applications with a singular focus on making AI genuinely work for India. Sarvam works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures. Sarvam partners with India’s leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC. About the Role Sarvam Agents bring AI into the way teams actually work. They plug into the tools and workflows of an organization (email, docs, calendars, internal systems, the long tail of SaaS), take multi-step action on a user's behalf, run on a schedule when no one is watching, and get better as the team uses them. Shared across the org, scoped by the right permissions, observable by admins. This is what agents look like when they have to actually work. We're hiring an Applied AI Engineer to build these agents and own them in production. You'll design the flows, wire up the tools, ship the harness, and be on the hook when something breaks. What You’ll Do - Build agents end-to-end: flow design, prompting, tool definitions, memory, evaluation, deployment - Own agent reliability in production: debugging real failures, designing guardrails, running incident response when things break - The agent runtime: state management, retries, scheduled triggers, long-running execution that keeps moving when no one is watching - Connector and integration framework: OAuth, third-party SaaS APIs, the plumbing that lets agents reach into real workplaces - MCP server infrastructure at scale: the tool layer agents reach for - Memory and context engineering: knowing when to use working memory vs. long-term memory vs. retrieval, and building the systems that make it work (Honcho and friends) - Multi-tenancy and sharing: agents that live inside organizations, with the right permissions, audit trails, and ad
Applying for this Applied AI Engineer, Sarvam Agents role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Ashby
- Ashby is a fast modern ATS — most applications take under 3 minutes.
- The resume parser is strong; verify parsed experience dates and job titles.
- Custom screening questions are often scored algorithmically — answer completely.
- Location field affects geo-based screening; use your actual metro area.
ANONYMOUS · UNFILTERED
What do employees actually say about Sarvam?
Real rants from real employees. Read before you apply.