Senior Forward Deployed Engineer, Gemini Enterprise Platform (GCP)

Zohorecruit; Bengaluru Urban; On-site; INR 1,800,000 - 2,600,000; Full time

Job summary

Zohorecruit in Bengaluru, India is seeking a Senior Forward Deployed Engineer to translate client use cases into production-ready Gemini Enterprise agents. You will embed with client teams, pair with their engineers, and deliver grounded, governed agents that scale in production environments.

You will design agent architectures, evaluate trajectories, and deploy on Cloud Run or GKE with IaC, driving adoption and measurable value for client outcomes.

Qualifications

• Master’s or Bachelor’s degree in CS/Engineering or equivalent practical experience.
• 6+ years building and shipping production software or ML systems, with strong Python.
• Hands-on experience building LLM agents with a code-first framework (ADK preferred; LangGraph, CrewAI, LlamaIndex or Amazon Bedrock Agents accepted).
• Strong BigQuery and SQL, and hands-on experience with at least one graph store (Spanner Graph, BigQuery graph, Neo4j or equivalent).
• Built at least one datapipeline in production (Dataform, Dataproc / Spark, dbt or equivalent) and worked with a streaming / eventing system (Pub/Sub or equivalent).
• Deployed services to a managed or container runtime (Cloud Run, GKE, Kubernetes or equivalent) within infrastructure-as-code (Terraform).
• Client-facing or embedded delivery experience — able to pair with a client's engineers and hand over cleanly.

Responsibilities

• Build agents ground-up in ADK and by forking and hardening Agent Garden templates — defining instructions, model selection, tools, orchestration and memory.
• Select and bind models per agent or per step for cost and latency; implement structured output, thinking-level and safety configuration.
• Run evaluation and simulation before ship — trajectory and response metrics, synthetic-user simulation and act on Agent Optimizer findings.
• Build MCP servers to expose client systems and data as agent tools; integrate off-the-shelf and third-party MCP servers; wire OpenAPI and Google Cloud toolsets.
• Implement multi-agent hand-offs where the design calls for them.
• BigQuery graph and context-grounding pipelines; develop data stack with Dataform, Dataproc, Pub/Sub; ensure cataloguing and governance.

Skills

Python

BigQuery

SQL

LLM agents

Data pipelines

Terraform

Cloud Run

GKE

Kubernetes

OpenAPI

Education

Master's or Bachelor's degree in CS/Engineering

Tools

ADK

LangGraph

CrewAI

LlamaIndex

Amazon Bedrock Agents

BigQuery graph

Job description

Bangalore South, India | Posted on 09/23/2026

You are theengineer who makes the outcome real. As a Senior Forward Deployed Engineer, youtake a client's use case from a whiteboard to a governed, evaluated agent thatpeople genuinely use — and you measure your work by the value it creates, notthe code you shipped. Embedded with the client, you build the agents, the toolsthey call and the context graph they reason over on the Gemini Enterprise AgentPlatform: composing them in ADK or on an Agent Garden template, grounding themon a BigQuery or Spanner Graph foundation, wiring them to data and systemsthrough MCP, deploying on Agent Engine / Cloud Run / GKE, and publishing theminto the client's Gemini Enterprise catalog.

You areclose enough to the client's engineers to pair with them, and close enough tothe platform to debug a failing agent trajectory — and disciplined enough toleave behind something the client can own, trust and extend.

This roleexists because the value of a Gemini Enterprise program is realised oneworking, adopted agent at a time — and that takes an engineer who can build toa production bar and operate credibly inside a client's environment.

DeploymentModel

Embedded ina client engagement, usually alongside a Principal Forward Deployed Architectwho owns the overall design. You pair with the client's own engineers and areexpected to leave them able to maintain and extend what you built. Somepre-sales support is expected — proofs of concept, demos and effort inputs.

KeyResponsibilities

Agentbuild

• Build agents ground-up in ADKand by forking and hardening Agent Garden templates — defininginstructions, model selection (Model Garden), tools, orchestration(LLM-driven and deterministic workflow agents), grounding and memory.
• Select and bind models peragent or per step for cost and latency; implement structured output,thinking-level and safety configuration.
• Run evaluation and simulationbefore ship — trajectory and response metrics, synthetic-user simulation —and act on Agent Optimizer findings.

Tools,MCP and integration

• Build MCP servers to exposeclient systems and data as agent tools; integrate off-the-shelf andthird-party MCP servers; wire OpenAPI and Google Cloud toolsets.
• Implement multi-agent (A2A)hand-offs where the design calls for them.

Contextgraph and data

• Build the context-graphfoundation on BigQuery graph (GQL) and/or Spanner Graph, and the retrieval/ grounding path (Vertex AI, Vector Search, Embeddings, RAG) that connectsit to agents.
• Build and operate thesupporting data stack: BigQuery models, Dataform pipelines, Dataproc jobsand Pub/Sub streams, with cataloguing, lineage and classification inDataplex Universal Catalog / Knowledge Catalog.

Deploy,operate and adopt

• Deploy agents to Agent Engine,Cloud Run or GKE via the Agents CLI and infrastructure-as-code; instrumentobservability (Cloud Trace / OpenTelemetry); apply governance (ModelArmor, Semantic Governance, Agent Identity).
• Publish agents into theclient's Gemini Enterprise app catalog and configure Google Workspaceintegration.
• Support adoption: onboardingmaterials, runbooks, and pairing with client users and engineers.

OutcomeOwnership

You own theoutcome of what you build — through production, handover and adoption.Grounded, evaluated, governed, deployed, documented, and actually used. Whenone of your agents fails, regresses or breaches a policy in production, you ownthe fix and the honest post-incident note.

Area

Technologies

Agent build (GEAP)

MCP & integration

MCP server development, off-the-shelf andthird-party MCP servers, A2A, OpenAPI, Google Cloud connectors / toolsets

Context graph & retrieval

BigQuery graph (GQL), Spanner Graph, Vertex AI, Vector Search, embeddings, RAG / grounding pipelines, entity resolution

BigQuery (SQL), Dataform, Dataproc (Spark), Pub/Sub,Python, Dataplex Universal Catalog / Knowledge Catalog

Quality & governance

Agent Evaluation (trajectory + autoraters), AgentSimulation, Agent Optimizer, Model Armor, Semantic Governance

MinimumQualifications

• Master's or Bachelor's degreein Computer Science, Engineering or a related field, or equivalentpractical experience.
• 6+ years building and shippingproduction software or data / ML systems, with strong Python.
• Hands-on experience buildingLLM agents with a code-first framework (ADK preferred; LangGraph, CrewAI,LlamaIndex or Amazon Bedrock Agents accepted) — including tools, retrievalgrounding and evaluation.
• Strong BigQuery and SQL, andhands-on experience with at least one graph store (Spanner Graph, BigQuerygraph, Neo4j or equivalent).
• Built at least one datapipeline in production (Dataform, Dataproc / Spark, dbt or equivalent) andworked with a streaming / eventing system (Pub/Sub or equivalent).
• Deployed services to a managedor container runtime (Cloud Run, GKE, Kubernetes or equivalent) withinfrastructure-as-code (Terraform).
• Client-facing or embeddeddelivery experience — able to pair with a client's engineers and hand overcleanly.

PreferredQualifications

• Hands-on with the GeminiEnterprise Agent Platform — ADK, Agent Garden, Model Garden, Agent Engine,Agent Studio, Agents CLI.
• Built or operated MCP servers,and integrated third-party MCP servers into an agent.
• Built a retrieval / groundinglayer over a knowledge or context graph.
• Experience with GeminiEnterprise app publishing and Google Workspace integration.
• Experience with agentevaluation and observability at production scale (autoraters, trajectorymetrics, Cloud Trace).