AI Engineer

Role Summary:

You build and own assigned solution streams across 1–2 concurrent projects. You implement agentic AI solutions on AWS AgentCore and LangGraph, contribute to POC delivery, and take full ownership of your components in production — including Pro Code builds and Low Code automations where the use case fits.

Key Responsibilities:

• Agentic AI Development
  
• Implement LangGraph agentic workflows on AWS AgentCore — state graphs, tool orchestration, conditional routing, error recovery.
  
• Build custom RAG pipelines end-to-end: chunking strategy, embeddings, vector retrieval, accuracy evaluation.
  
• Contribute to rapid POC delivery alongside the Architect and Lead.
  
• Write production-grade Python with FastAPI, Pydantic, testing, and proper error handling.
  
• Use AI coding tools (Claude Code, GitHub Copilot, Cursor, Cline) to accelerate builds. Own and fix all generated code in production.
  
• Low Code & Automation
  
• Build Low Code automations using Microsoft Copilot Studio and Power Automate when use case and bandwidth allow.
  
• Understand Pro Code vs Low Code trade-offs — flag where Low Code is the better fit.
  
• Stay current on Low Code platform capabilities as they expand rapidly.
  
• Production Ownership & Collaboration
  
• Own assigned components in production — monitor, debug, optimise, iterate.
  
• Debug agent failures independently: context issues, tool errors, hallucination, retrieval degradation.
  
• Collaborate with the Lead on architecture translation and implementation planning.
  
• Mentor Associate Developers through code reviews and pair programming.
  

Required Skills & Experience:

Must Have:

• LangGraph — State graphs, conditional routing, checkpointing — primary framework, non-negotiable.
  
• LangChain — Chains, memory, custom tools — solid foundational knowledge.
  
• AWS AgentCore — Hands-on preferred; strong LangGraph depth with ramp path acceptable.
  
• AWS Bedrock — Model invocation, knowledge bases, guardrails.
  
• Database & AI Data Access — SQL proficiency, NL-to-SQL, LLM-powered query and insight patterns. Snowflake a plus.
  
• RAG Pipelines — End-to-end: chunking, embeddings, retrieval, evaluation.
  
• Vector Databases — Pinecone, ChromaDB, OpenSearch, or FAISS — hands-on with at least one.
  
• Python — Production-quality — type hints, async/await, FastAPI, Pydantic.
  
• Multi-Model — OpenAI, Claude, Gemini, Llama — understand trade-offs across providers.
  
• Pro Code vs Low Code — Copilot Studio and Power Automate — build when use case fits.
  
• AI Development Tools — Claude Code, GitHub Copilot, Cursor, or Cline — accelerate delivery; own and fix all generated code.
  
• Experience — 3–5 years total; 1–2 years GenAI/LLM; 6–12 months LangGraph; 2–3 projects with working code.
  

Good to Have:

• AWS AgentCore Deep — Runtime, Memory, Tools Gateway hands-on.
  
• MCP / A2A — Server/client implementation or protocol awareness.
  
• Enterprise Integration — SAP HANA, Salesforce connectors.
  
• Document Intelligence — OCR, layout-aware chunking.
  
• Evaluation Frameworks — RAGAS, Promptfoo, DeepEval.
  
• Certifications — AWS, GCP, or Azure AI/ML.
  

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.