AI Architect- Agentic Data Modernization (IDM Platform)

AI Architect — Agentic Data Modernization (IDM Platform)
Designation: Manager / Senior Manager 
Responsibilities: 
• Design multi-agent orchestration frameworks using Lang Graph — stateful graphs, 
conditional routing, agent handoff, retry and fallback logic
• Build agent harnesses coordinating Discovery, Parsing, Mapping, Code Generation, 
Validation, and Review agents across a shared execution context
• Develop the IDM prompt library — system prompts, few-shot templates, structured 
output schemas, and reflection loops for each conversion workstream
• Build LLM-powered code conversion pipelines ex: DataStage → Databricks PySpark, 
Dremio SQL → Snowflake SQL, legacy ETL → cloud-native equivalents
• Lead AICH–IDM platform integration — capability merger, MCP server design, 
shared tool registry, unified agentic execution surface
• Architect and operate conversion pipelines for 50,000–80,000+ legacy objects with 
parallelism, batching, resumability, and audit logging
• Build metadata frameworks for conversion traceability — extraction run tracking, 
job dependency graphs, column-level lineage, confidence scoring
• Implement LLM routing layers that select models (Claude, OpenAI, Azure OAI) 
based on task type and quality requirements
• Build and maintain IDM backend services — FastAPI, Celery/Redis, LangGraph 
runtime, CI/CD integration
• Surface agent observability — token usage, latency per hop, model selection audit 
trail, output quality metrics
Technical Skills Expected 
• LangGraph — production-grade stateful graph design, interrupt/resume, shared 
memory, conditional edges
• LLM APIs — Anthropic Claude, OpenAI, Azure OpenAI; tool use, structured outputs, 
prompt construction at scale
• Python — async, FastAPI, Pydantic, Celery, Redis
• Prompt engineering — few-shot design, chain-of-thought, output parsers, selfconsistency, reflection loops; not just RAG chat patterns
• Metadata-driven architecture — YAML config-driven generation, schema inference, 
column-level lineage design
• MCP server design and tool registration
• Vector stores and RAG
• Claude Code — experience using Claude Code as an agentic coding harness
• SKILL.md / prompt library design — ability to design and maintain skill files that 
encode conversion rules, output constraints, and few-shot patterns as versioned, 
reusable assets loaded by the harness at runtime 
Technical Skills Good to Have
• Legacy ETL platforms — DataStage, Informatica etc; enough depth to understand 
what the agent is converting
• Databricks — PySpark, notebooks, Unity Catalog, Delta Lake
• Snowflake — SQL, Snowpark, DDL generation patterns
• AWS — S3, Glue, Lambda; IAM and data lake patterns
• Apache Iceberg — table format internals, catalog integration
Experience
• 10 - 15 years total experience 
• 1-2 years building production LLM systems beyond chatbots 
• One enterprise-scale legacy data migration program preferred 
• Consulting background preferred
• Agile based delivery experience.