Technical Architecture & DeliveryLead architecture decisions across the portfolio — schema design, API contracts, integration patterns, workflow orchestration, and when to integrate via direct API versus MCP (Model Context Protocol), weighing latency, control, security, auditability, and reusability tradeoffsHold delivery accountability — scope, timeline, quality — across all active workstreams, in partnership with the Director who owns product requirements and prioritizationDesign and own the Postgres data schema underpinning the product (multi-table: pipeline data, access control, cost attribution, audit) — correctness and extensibility here is foundational, not incidentalBuild and own the Claude/API integration layer: system prompt design and testing, multimodal document ingestion for XLSX, DOCX, PPTX, and PDF via reliable extraction/conversion pipelines, structured output parsing, schema validation, and fallback handlingDesign practical automation workflows — background jobs, queues, retries, idempotency, human review points, run state, and replayable audit history for multi-step AI-assisted processesBuild and own third-party DSP API integrations (e.g. DV360, TTD) — OAuth flows, structured data file formats, read/write scoping by phaseDesign and own secrets and credential management — API keys, OAuth credentials, Azure Key Vault or equivalent secrets manager; nothing in code or setting variables in source controlDesign and own multi-tenant access control — role-based permissions, client-scoped data visibility,



self-service onboardingDesign cost and usage attribution patterns — external API calls tagged and logged at the client and run level, feeding finance and program-level reporting as the portfolio scalesReview technical output against product requirements — flag when implementation doesn't match the requirement or the architecture is wrong for the problemTeam LeadershipManage a team of junior and mid-level developers based in India — hiring input, onboarding, performance, growth planningRun code reviews, pairing, and technical mentoring as a standing practice, not an occasional oneSet and enforce engineering standards: testing discipline, data validation, AI evaluation discipline, observability, and code quality barStandardize how the team uses Claude Code — establish shared conventions, prompt/context patterns, and reusable practices so the whole team improves its delivery quality, not just youRun sprint-level technical planning and unblock the team day to day; escalate cross-team blockers to the Director rather than letting them stall deliveryBuild ExecutionBuild full-stack applications end to end where needed: Python APIs (FastAPI or similar) and React/Tailwind front endsUse Claude Code as a daily driver — both for personal output and as the standard tool your team is held toWrite tests, build data validation frameworks, and instrument observability across the pipeline, including prompt/model traces, structured-output validation, latency, cost, and failure analyticsBuild and maintain practical evaluation harnesses for AI behavior — golden test sets, prompt/model versioning, regression checks, failure taxonomies, and release gates for higher-risk automationsContribute to reusable component lib

📌 Engineering Lead (AI & Automation Products) (Mumbai)
🏢 Dentsu Global Services
📍 Mumbai