Senior Technology Lead – Agentic AI & Legacy Modernization

Job Role: Senior Technology Lead – Agentic AI & Legacy Modernization

Location: Jersey City, NJ (Hybrid)

Duration: Contract for 06+ Months

Job Description:

• We are seeking a Senior Technology Lead who sits at the intersection of **agentic AI, legacy modernisation, and cloud-native engineering**. This is not a role about using AI as a productivity shortcut — it is about designing and deploying custom AI agent pipelines that systematically reverse-engineer legacy estates and forward-engineer modern cloud-native platforms at a pace and depth that human-only approaches cannot match.
• You will develop and operate AI-driven modernisation workflows, produce detailed solution designs, lead a cross-functional engineering team, and own delivery commitments end-to-end. You write the agents, you write the designs, you do the code reviews, and you set the engineering bar.

Legacy estates in scope typically include:

• Mainframe COBOL/CICS/IMS batch and online transaction processing
• Hierarchical and relational databases (IMS, DB2) with deeply embedded business logic
• Proprietary messaging middleware (IBM MQ) and brittle point-to-point integrations
• Legacy OO platforms (VisualAge Smalltalk, Tonel format) with no test coverage or documentation
• JCL/Assembler job streams woven into business-critical workflows
• Your mission: deploy **AI agent chains** to extract, analyse, and understand this estate at depth — then drive **forward engineering** onto a modern Spring Boot / Java 21 / Angular / MongoDB cloud-native stack, with AI agents accelerating design, code generation, test authoring, and migration validation at every step.

Required Skills & Experience

• Agentic AI Engineering (Must-Have)
• Hands-on experience building **multi-agent systems** using at least one platform: **Claude Code CLI**, **Cursor**, **Gemini CLI**, LangChain/LangGraph, AutoGen, CrewAI, or equivalent
• Ability to design agent orchestration patterns: sequential chains, parallel fan-out, supervisor/worker hierarchies, reflection and self-critique loops
• Experience with **tool use / function calling** in LLM agent contexts — designing custom tools agents invoke to read codebases, query databases, call APIs, or run test suites
• Working knowledge of **agent memory strategies**: in-context state, vector store retrieval (RAG), structured external memory
• Practical **prompt engineering** for code tasks: extraction, generation, validation, and iterative refinement prompts
• Experience evaluating agent output quality; ability to design human-in-the-loop review workflows and validation harnesses
• Familiarity with **LLM APIs**: Anthropic Claude, Google Gemini, OpenAI GPT-4o, or equivalent; understanding of context limits, token budgets, and cost management at scale
• Agentic AI Platforms —
• **Claude Code CLI** Agentic coding sessions, MCP tool integration, custom slash commands, BMAD/GSD agent workflows
• **Cursor** AI-native IDE, codebase-indexed agents, .cursorrules enforcement, multi-file refactoring
• **Gemini CLI** Long-context legacy codebase analysis, Google ecosystem integration, structured output pipelines
• **LangChain / LangGraph** Complex stateful agent chains, tool registries, conditional routing, legacy extraction pipelines
• **AutoGen / CrewAI** Role-specialised multi-agent teams for parallel workstreams (extractor + validator + generator)
• Modernisation & Legacy Expertise
• 15+ years of software engineering; 3+ years in a tech lead, engineering solution designer role
• Ability to read and reason about **COBOL, CICS transaction logic, IMS hierarchical data structures** — extracting business intent
• Experience designing **strangler-fig**, **anti-corruption layer**, and **event interception** patterns in production migration contexts
• Familiarity with **dual-write / dual-read** strategies and zero-downtime data migration pipeline design
• Modern Forward Engineering Stack (Must-Have)
• Deep expertise in **Java 21** — virtual threads, records, sealed classes, pattern matching — and **Spring Boot 3.x**: REST, Security, Data, actuator, event-driven patterns
• **MongoDB** — document schema design for migration from relational/hierarchical models, aggregation pipelines, indexing strategy
• **Angular / TypeScript** — component architecture, RxJS, HTTP client, module boundaries replacing legacy UIs
• **O…