Solutions Architect

Solution Architect - (Google Cloud, Agentic GenAI, MCP)Role summaryPeople Tech Group is seeking a hands-on Solution Architect to design and lead anindustrial Integrity Operating Window (IOW) AI platform for a leading refinery. You will ownthe end-to-end architecture across GCP data services, event/middleware, agentic GenAI(MCP microservices per source), and the AI & knowledge base layer (RAG over standardslike API 571/584 and SOPs) - delivering a secure, real-time, expert-in-the-loop systemLocation: India (preferred IST timezone)Function: Engineering/ArchitectureType: Full-timeResponsibilities: - Own the reference architecture: Translate business & SME needs into a cloudnative,real-time architecture spanning on-prem connectors(PI/IOW/LIMS/APM/ERP/Logbook) → MCP adapter layer → event bus → agentic AI →dashboard & workflows Design MCP layer (per-source microservices): Define APIs, schemas, and contractsfor MCP-PI, MCP-IOW/LIMS, MCP-APM, MCP-ERP, MCP-Logbook; standardize ondemandaggregates (24h/7d/30d/90d), normalized events, retries, and backpressure Evented core: Architect and tune Pub/Sub (or Kafka) topics fordeviations/alarms/actions; ensure idempotency, ordered processing whererequired, and replay strategy AI & knowledge base: Lead agentic GenAI design—Data Analysis Agent (tool useover MCPs), Knowledge Agent (RAG over standards like API 571/584, vendormanuals, SOPs), Expert-Feedback Agent (thumbs/annotations loop), Orchestrator(GPT-class LLM) RAG & vector search: Choose and implement vector store (Cloud SQL + pgvector,Vertex AI Matching Engine, or Milvus); define chunking, embeddings, refreshcadence, grounding/citations Security & governance by design: Enforce VPC/VPN/Interconnect, IAM (leastprivilege/service accounts), Cloud KMS (CMEK), Cloud Audit Logs, Data Catalog &Lineage, DLP & data quality rules, SSO/OIDC Data services & middleware: Select and size Cloud Run/GKE for MCPs & BFF, CloudStorage for docs/dumps, Memorystore for feature cache, optional BigQuery(analytical store) without coupling runtime Integration workflows: Orchestrate Action Tracker ↔ ERP (SAP PM/Oracle EAM) viaMCP-ERP; define SLAs, ownership, and auditability for IOW→RBI hand-os (GE APM) Observability & SLOs: Establish metrics, traces, logs, and SLOs (latency, freshness,accuracy), plus runbooks for incident response Cost & scale: Model infra + LLM cost envelopes, implement autoscaling,request/response token budgets, and caching strategies Delivery leadership: Produce architecture docs, ADRs, sequence diagrams; guidedevelopers, data/ML engineers, and MLOps; engage SMEs (operations,corrosion/RBI) for iterative validationRequired qualifications 10+ years in distributed systems/data/AI architecture with at least 3+ years on GCPleading production solutions Proven design of event-driven architectures with Google Pub/Sub (or Kafka), andmicroservices on Cloud Run or GKE Strong with GCP data stack: Cloud Storage, Cloud SQL/Postgres (pgvector),Dataflow/Data Fusion (or equivalent ETL), Cloud Monitoring, Cloud Logging, SecretManager, IAM, KMS, VPC Hands-on GenAI + RAG: embeddings, vector search, grounding/citations, prompttooling, and safety/guardrails; experience integrating OpenAI/Vertex AI (Gemini) orAnthropic models MCP-style adapter design: built source-specific microservices/APIs that normalizeschemas, perform windowed aggregates, and publish events Integration exposure to OSIsoft PI/PI Web API, IOW/LIMS, GE APM (RBI), andSAP/Oracle ERP (REST, OData, queues, or middleware) Practical security & compliance: IAM design, network segmentation, CMEK,auditability, lineage; understands safety-critical environments Excellent stakeholder skills: can translate SME input (e.g. API 571/584, IOWpractices) into technical decisionsNice-to-have (preferred) LLMOps/MLOps: Vertex Pipelines, model registries, prompt/versioning, evals, ABtests, telemetry Action management integrations (SAP PM/Maximo), Apigee/API gateway exposure Time-series modeling (feature engineering, basic LSTM/TFT/Prophet, or XGBoostclassifiers for risk scoring) Graph/causal modeling for chain-link analysis (propagation across units) Experience hardening BFF/API layers, RBAC in UI, and expert-feedback/annotationUX Oil and Gas Industrial domain: Refining, IOW (knowledge on standards like API RP571/584), corrosion loops, RBI workflows