kAIgentic
kAIgentic
kAIgentic is a Singapore-headquartered enterprise AI SaaS company helping complex, knowledge-intensive organizations turn tacit operational knowledge into governed AI agents. Its platform combines agent configuration, diagnostic analysis of people, systems, and processes, and a runtime environment for deployment with human oversight, telemetry, and ongoing refinement. With roots in Japan and enterprise financial-services collaboration, kAIgentic focuses on assurance, compliance, and practical AI modernization for regulated businesses without requiring a rip-and-replace approach.

Software Engineer, AI Research — Bengaluru Hybrid

Build enterprise AI infrastructure across document intelligence, GraphRAG, retrieval systems, and secure multi-agent integrations. The role combines production engineering with applied AI research.

Description

  • Develop complete document-ingestion pipelines that handle layouts, tables, scanned diagrams, and long-form content embeddings
  • Create schema-constrained LLM extraction systems with typed schemas, validation loops, and automated repair or reprompt cycles
  • Lead retrieval engineering across hybrid search, reranking, and query expansion
  • Build knowledge graphs and entity-resolution pipelines with Neo4j or comparable property-graph stores to support GraphRAG retrieval
  • Strengthen grounding by combining terminology stores with retrieval-in-the-loop generation
  • Partner with product and research teams to establish evaluation datasets, grading rubrics, and regression gates
  • Develop planner-worker multi-agent orchestration and tool routing with native SDKs
  • Lead MCP and agent-to-agent integrations with secure contracts, authentication boundaries, and cross-service context passing

Requirements

  • Demonstrated success delivering production AI systems in Python with strong typing, comprehensive tests, and asynchronous pipeline design
  • A working style centered on fast, AI-native development
  • Advanced understanding of LLM prompting, schema-based extraction, and automated repair loops
  • Expertise in dense embeddings, hybrid search, reranking, and query expansion
  • Experience operating property-graph databases such as Neo4j and building entity-resolution and GraphRAG pipelines
  • Practical experience with grounding architectures, terminology stores, and retrieval-in-the-loop generation
  • Proficiency with multi-agent orchestration tools such as LangGraph or the OpenAI Agents SDK, plus secure MCP or A2A integration patterns
  • Experience designing evaluation datasets, building graders, and implementing regression tests with tracing tools such as Langfuse
  • Sound judgment when balancing research goals against product requirements
  • Ability to communicate clearly with engineers, product managers, and senior stakeholders

Benefits

  • Meaningful ownership from the start
  • Opportunities to learn and grow alongside experienced leaders from major enterprises
  • A trust-based culture supporting psychological safety, open disagreement, and disciplined experimentation
  • Work with colleagues across Singapore, India, Japan, Europe, and the United States

Related Jobs