Principal AI Engineer - Hybrid in Bangalore

You Will:

• Own the target-state architecture for Smartsheet's AI platform, defining the standards that bind Data, Agents, Knowledge Graph, Context Graph into one coherent system.
• Set the architecture for the agent harness and sub-agent framework including orchestration, lifecycle, hand-off contracts, Evals (Offline and Online) and capability-tier classification used across all agent teams.
• Design and own schema/ontology, ingestion and freshness pipelines, and the retrieval and grounding patterns that keep agent responses reliable.
• Build and maintain a reference agent framework that teams fork or extend, so no team re-solves orchestration, tracing, or deployment from scratch.
• Author and publish a shared skills and tools library with clear interface contracts and a versioning model any team can build on.
• Stand up fast, slim prototypes to de-risk architecture decisions (new sub-agent patterns, retrieval strategies, partner capabilities) before teams commit a roadmap to them, and own the criteria for promoting a prototype into a supported, shared capability.
• Define deployment, security, and governance patterns, including the standard path from prototype to production and the AI governance plane applied across platforms and agents.
• Serve as Smartsheet's primary technical lead for strategic technology partners — Databricks (Lakehouse, Unity Catalog, Unity AI Gateway), AWS (Bedrock, AgentCore), Anthropic (Claude, MCP, agent patterns),and others — running standing technical syncs and routing early-access programs through prototypes evaluated against real Smartsheet problems.
• Partner closely with Principal Engineers and team leads across Smartsheet, aligning to platform milestones through architecture authority in design and demonstrated prototypes.
• Engage with Forward Deployed Engineering (equipping the field team with reference frameworks and skills) and MCP/external parity (reviewing gate criteria before external commitments).
• Drive architecture decisions to close quickly and keep the escalation backlog near zero.

You Have:

• Deep, hands-on experience architecting production agentic systems on Databricks Platform, AWS Bedrock/AgentCore and MCPs
• Experience in Agent harness/orchestration design, sub-agent boundaries, tracing and observability (e.g., MLflow), Evals, Governance, Responsible AI and cost/latency instrumentation at platform scale.
• Strong background in Knowledge and Context graph based systems, including ontology design, ingestion pipelines, and retrieval/grounding evaluation.
• A builder's track record: you prototype rapidly, ship working software, and let adoption — not mandate — prove which patterns are right.
• Experience designing reusable, versioned software interfaces (skills, tools, libraries) that multiple teams adopt directly, with clear contracts and promotion criteria from prototype to production.
• Familiarity with modern LLM/agent tooling and standards, including Databricks, Bedrock, Strands SDK, and MCP (Model Context Protocol).
• Comfort operating as a technical DRI in strategic partner relationships (e.g., Databricks, AWS, Anthropic), translating partner roadmaps and early-access capabilities into platform decisions.
• Proven ability to set cross-team technical standards and drive alignment without formal management authority — influencing through design quality, working prototypes, and clear documentation rather than positional control.
• Strong judgment on architectural tradeoffs spanning model selection, inference patterns, deployment, and governance, balanced with respect for team-level autonomy over delivery.
• Excellent cross-functional communication skills and translating ambiguity into documented, decisive architecture calls.
• Legally eligible to work in India on an ongoing basis