Overview

Engineer lead architect ai automation

Key Responsibilities

• Lead 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 tradeoffs.
• Hold delivery accountability — scope, timeline, quality — across all active workstreams, in partnership with the Director who owns product requirements and prioritization.
• Design 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 incidental.
• Build 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 handling.
• Design practical automation workflows — background jobs, queues, retries, idempotency, human review points, run state, and replayable audit history for multi-step AI-assisted processes.
• Build and own third-party DSP API integrations (e.g. DV360, TTD) — OAuth flows, structured data file formats, read/write scoping by phase.
• Design and own secrets and credential management — API keys, OAuth credentials, Azure Key Vault or equivalent secrets manager; nothing in code or environment variables in source control.
• Design and own multi-tenant access control — role-based permissions, client-scoped data visibility, self-service onboarding.
• Design 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 scales.
• Review technical output against product requirements — flag when implementation doesn't match the requirement or the architecture is wrong for the problem.

Team Leadership

• Manage a team of junior and mid-level developers based in India — hiring input, onboarding, performance, growth planning.
• Run code reviews, pairing, and technical mentoring as a standing practice, not an occasional one.
• Set and enforce engineering standards: testing discipline, data validation, AI evaluation discipline, observability, and code quality bar.
• Standardize 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 you.
• Run sprint-level technical planning and unblock the team day to day; escalate cross-team blockers to the Director rather than letting them stall delivery.

Build Execution

• Build full-stack applications end to end where needed: Python APIs (FastAPI or similar) and React/Tailwind front ends.
• Use Claude Code as a daily driver — both for personal output and as the standard tool your team is held to.
• Write tests, build data validation frameworks, and instrument observability across the pipeline, including prompt/model traces, structured-output validation, latency, cost, and failure analytics.
• Build and maintain practical evaluation harnesses for AI behavior — golden test sets, prompt/model versioning, regression checks, failure taxonomies, and release gates for higher-risk automations.
• Contribute to reusable component libraries and shared platform services that scale across clients and future portfolio products.

Required Skills

• 13–16 years of professional software engineering experience with deep Python expertise.
• Demonstrated experience leading or managing a team of engineers — code review, mentoring, growth planning — not just individual contribution.
• Strong experience designing and building production APIs in Python (FastAPI, Flask, or similar) and full-stack applications including React + Tailwind CSS front ends.
• Strong relational database experience — schema design, normalization, query performance — Postgres preferred.
• Strong practical proficiency with Claude Code or similar AI-assisted development tools, including agentic coding patterns and context management — and the ability to establish team standards for effective use.
• Experience integrating LLM APIs (Claude, OpenAI, or equivalent) into production systems — system prompt design, structured output parsing, multimodal input handling.
• Practical experience with tool-use/function-calling patterns — defining tool schemas, validating arguments, handling tool results, chaining tool calls, and managing basic failure/retry behavior.
• Strong context engineering fundamentals — context window management, token budgeting, long-document handling strategies, and retrieval/context-selection patterns.
• Awareness of prompt injection, adversarial inputs, and untrusted-document risks in AI systems; ability to design guardrails for external briefs, trafficking sheets, platform exports, and other model-readable inputs.
• Experience integrating third-party platform APIs with OAuth (any domain) — general competency, not platform-specific.
• Working knowledge of secrets management and credential security practices in production systems, ideally including Azure Key Vault or equivalent managed secrets tooling.
• Solid grasp of QA practices, data quality engineering, and AI evaluation: unit and integration testing, data validation, golden datasets, regression evals, structured-output checks, and observability.
• Practical understanding of human-in-the-loop AI systems — adjudication workflows, labeled examples, accuracy measurement by parameter/category, feedback loops, and quality gates.
• Experience with cloud infrastructure (Azure preferred) and modern deployment patterns: containers, CI/CD, managed identities, object storage, and background job/workflow execution.
• Experience implementing background-processing or workflow patterns — queues, scheduled jobs, retries, idempotency, status tracking, and operational monitoring.
• Strong written and verbal communication for collaboration across distributed onshore (US) and offshore (India) teams.

Preferred Skills

• Exposure to LLM application and workflow frameworks beyond raw API calls: LangChain, LangGraph, CrewAI, Temporal, Azure Durable Functions, Celery/RQ, or equivalent agent/workflow tooling — useful as the portfolio expands into durable, multi-step automation in later phases.
• Exposure to model selection and cost optimization strategies — prompt caching, batching, tiered model selection by task complexity, latency/cost tradeoff analysis, and usage forecasting.
• Background in media, advertising, or marketing technology data environments.
• Exposure to data governance tooling such as Unity Catalog, attribute-based access control, or tag-driven policies.
• Exposure to MCP servers or MCP-based developer workflows, with interest in when MCP is preferable to direct APIs for reusable tools, resources, prompts, and agent context.
• Exposure to data flywheel concepts — labeled corpora, adjudication data models, feedback capture, quality dashboards, and mechanisms that improve future AI behavior and inform phase-gate decisions.
• Exposure to DV360 SDF (Structured Data Files), TTD API, or comparable adtech platform data formats/APIs.
• Open-source contributions or public projects demonstrating full-stack or AI engineering work.

Other Details

• 13 years
• Remote
• 6 months
• US Shift (06:00 PM - 03:00 AM IST)