Senior AI Engineer – Agentic AI, LLM & Knowledge Graphs

Position Summary

We are seeking an experienced Senior AI Engineer to design, build, and operate production-grade AI systems that enable end-to-end customer experiences, increase straight-through processing, and optimize technology capabilities. The ideal candidate will have hands-on experience delivering LLM and Generative AI solutions beyond the prototype stage, with strong software engineering and production operations expertise.

Required Skills & Experience

• 6–10 years of production software engineering experience, including hands-on delivery of AI/LLM systems.
  
• Strong Java/JVM engineering experience; Kotlin or Scala preferred.
  
• Strong software engineering practices including Git, code reviews, automated testing, structured logging, and clean design principles.
  
• Hands-on experience with GenAI patterns including prompt engineering, structured/JSON outputs, tool/function calling, RAG, and agentic workflows.
  
• Experience with Neo4j/Cypher and/or MongoDB Atlas.
  
• Experience with vector search and embeddings for semantic retrieval.
  
• Strong expertise in Agentic AI, Knowledge Graphs, GraphRAG, AI-enabled document generation, cloud infrastructure, CI/CD, and observability.
  
• Experience with MCP (Model Context Protocol) and/or A2A (Agent-to-Agent) interfaces is highly desirable.
  

Key Responsibilities

• Design and build long-running, multi-stage agentic workflows that can pause, resume, and recover reliably.
  
• Orchestrate LLMs and tools for retrieval, calculations, rules, and structured extraction.
  
• Engineer prompts and structured-output contracts to produce validated, machine-readable results.
  
• Build event-sourced workflows using frameworks such as Akka SDK, with persistent state, decisions, and evidence.
  
• Design and maintain knowledge graphs containing entities, relationships, and source provenance.
  
• Develop ingestion and extraction pipelines that transform source documents into validated, queryable graph structures.
  
• Implement GraphRAG, vector retrieval, and embeddings to provide grounded AI responses.
  
• Develop MCP tool servers and A2A interfaces and integrate with MCP-compatible clients and platforms such as Microsoft Copilot Studio.
  
• Establish grounding, evaluation, and safety standards, including anti-hallucination controls, regression testing, edge-case testing, and human-in-the-loop reviews.
  
• Implement guardrails for prompt injection, data minimization, and safe AI output generation.
  
• Own the complete lifecycle from development through production deployment and operations.
  
• Build and maintain CI/CD pipelines, environment configurations, secrets management, and access controls.
  
• Work with enterprise AI services including managed model endpoints, search/retrieval services, document storage, OCR/document intelligence, and graph databases.
  
• Implement logging, metrics, tracing, monitoring, and alerting for production AI systems.
  
• Collaborate with engineering, business, and technology stakeholders to deliver secure, explainable, reliable, and business-ready AI solutions.