Role Summary
Senior individual contributor across 4–5 concurrent projects. You engage Business and Transformation Leaders to assess feasibility, deliver POCs in 1–4 weeks, define solution architecture, and build the complex pieces yourself. The quality of your upfront design determines how fast the team builds and how clean the testing is.
Key Responsibilities
- Business Engagement & Feasibility
- Meet Business and Transformation Leaders to understand pain points and assess AI solution feasibility.
- Recommend Pro Code (LangGraph/AgentCore) or Low Code (Copilot Studio/Power Automate) based on the use case — document and communicate the rationale.
- Deliver working POCs within 1–4 weeks. Evaluate Forward Engineer POCs and decide to scale or rebuild based on quality.
- Present feasibility and POC outcomes to business stakeholders with clear scope, effort, and value framing.
- Architecture & Design
- Define solution architecture on AWS AgentCore and LangGraph — the primary stack for all Pro Code solutions.
- Invest heavily upfront in design robustness: strong architecture enables smooth builds; weak architecture amplifies every downstream problem.
- Design systems integration: API architecture, MCP connections, database and data platform access patterns, SAP, Salesforce, and internal systems.
- Define agent state management, tool orchestration, human-in-the-loop escalation, and data flow.
- Ensure all solutions comply with TR's established security, governance, and compliance standards.
- Continuously evaluate emerging agentic AI frameworks, platform updates, and industry patterns — provide evidence-based recommendations on adoption timing and fit for TR's stack.
- Hands-On Build & Team Leadership
- Build complex and architecturally critical solution components directly — this is a coding role.
- Guide the Solutions Lead, Developer, and Associate through architecture, implementation patterns, and production readiness.
- Enable the Lead to own day-to-day decisions during build by ensuring architecture is unambiguous before stepping back.
- Use AI coding tools (Claude Code, GitHub Copilot, Cursor, Cline) to accelerate POC and development. Own all generated code fully.
Required Skills & Experience
Must Have:
- AWS AgentCore — Runtime, Memory, Tools Gateway — production hands-on required.
- LangGraph — Multi-agent state machines, conditional routing, checkpointing, HITL — primary framework.
- LangChain — Advanced chains, memory, custom tool integration.
- AWS Bedrock — Multi-model deployment, knowledge bases, guardrails.
- Database & AI Data Access — SQL proficiency, NL-to-SQL, LLM-powered query and insight layers. Snowflake a plus.
- Systems Integration — API design (REST), MCP server/client, A2A patterns, SAP/Salesforce/internal system connectors.
- RAG Architecture — Hybrid search, re-ranking, agentic RAG, graph RAG — select and justify per use case.
- Multi-Model Strategy — OpenAI, Claude, Gemini, Llama — provider trade-offs and cost governance.
- Pro Code vs Low Code — Evaluate each use case and recommend. Copilot Studio and Power Automate for the right automation scenarios.
- AI Development Tools — Claude Code, GitHub Copilot, Cursor, or Cline — accelerate delivery; own and fix all generated code in production.
- Python — Expert-level production code — you write, review, and fix code.
- Production Deployment — Docker, CI/CD, post-deployment monitoring, cost optimisation.
- Business Communication — Present feasibility and POC outcomes to business leaders clearly.
- Cloud Adaptability — Google Agentspace and Azure AI Foundry exposure welcome — AWS is the primary stack.
- Experience — 10+ years total; 3–5 years solution architecture with direct delivery accountability; production agentic AI systems deployed.
Good To Have
- MCP / A2A — Production server/client implementations.
- Document Intelligence — Azure Document Intelligence, Textract, layout-aware chunking.
- Fine-Tuning — LoRA / QLoRA for domain adaptation.
- Graph Databases — Neo4j for knowledge graph RAG.
- Domain Experience — Legal, financial, or regulatory AI applications.
- Certifications — AWS Solutions Architect Pro, Google Professional Cloud Architect, Azure Solutions Architect Expert.
What We Expect From You
- Customer Obsession
- Proactively understand customer goals and deliver measurable value.
- Competitive Drive
- Set high standards, demonstrate tenacity, and ensure our solutions lead in quality.
- Challenging Mindset
- Foster fact-based dialogue, challenge assumptions, and encourage disruptive thinking.
- Action and Learning Velocity
- Build fast, fail fast, learn fast. Iterate rapidly and make data-driven decisions.
- Collaboration and Accountability
- Collaborate across a global team with humility, ownership, and mutual accountability.
Why Join Us
- Build production agentic AI at global scale — real systems, real impact.
- Work with AWS AgentCore, LangGraph, MCP, A2A, and AI-powered development tools.
- Operate in a high-trust team where Architect, Lead, Developer, and Associate work in sync.
- A culture of rapid learning, fast iteration, and genuine technical excellence.
