Job Description: Principal Software Engineer – AI Platforms & Knowledge Graphs

Role: Principal Software Engineer – AI/LLM Platforms

Experience: 10–15+ years

Level: Principal Engineer / Technical Architect

Domain: Enterprise AI, Knowledge Graphs, Generative AI, Distributed Systems

About the Role

We are looking for a highly accomplished Principal Software Engineer to lead the architecture, design, development, and evolution of enterprise-scale AI platforms, knowledge graph systems, and intelligent applications.

The ideal candidate brings deep expertise in distributed systems, scalable software architecture, knowledge graphs, Large Language Models (LLMs), and production-grade AI engineering.

This is a hands-on technical leadership role requiring strong engineering fundamentals, architectural depth, and the ability to build, deploy, scale, and maintain complex AI-powered systems for enterprise customers.

The candidate should have practical experience working with multiple LLMs, understand their capabilities, limitations, and performance trade-offs, and be capable of making informed architectural decisions to deliver reliable, secure, and cost-efficient AI solutions.

Key Responsibilities

1. Enterprise Knowledge Graph Engineering

- Architect, design, develop, and maintain scalable enterprise knowledge graph platforms.

- Build knowledge ingestion, entity extraction, relationship mapping, entity resolution, and graph enrichment pipelines.

- Design graph data models, ontologies, taxonomies, and semantic relationships.

- Develop high-performance graph querying, retrieval, and reasoning capabilities.

- Integrate knowledge graphs with enterprise data sources, applications, and AI systems.

- Implement GraphRAG, hybrid retrieval, and context-aware search architectures.

- Ensure scalability, reliability, data consistency, and performance of graph-based systems.

2. AI & LLM Platform Engineering

- Lead the architecture and development of production-grade AI applications leveraging Large Language Models.

- Design and implement RAG, GraphRAG, agentic AI, and intelligent workflow solutions.

- Integrate and orchestrate multiple proprietary and open-source LLMs, including GPT, Claude, Gemini, Llama, and other emerging models.

- Evaluate LLM capabilities, reasoning quality, latency, context handling, accuracy, cost, and suitability for different use cases.

- Develop model-agnostic architectures enabling flexible model selection, routing, and fallback strategies.

- Optimize prompt engineering, context management, inference performance, token consumption, and operational costs.

- Build LLM evaluation frameworks, monitoring, guardrails, and observability capabilities.

- Address hallucinations, retrieval quality, grounding, security, and reliability challenges in enterprise AI applications.

3. Scalable Systems Architecture

- Architect highly scalable, fault-tolerant, distributed systems supporting enterprise workloads.

- Design cloud-native, microservices-based, asynchronous, and event-driven architectures.

- Build high-throughput data pipelines and low-latency APIs.

- Drive performance engineering, horizontal scaling, caching, concurrency, and infrastructure optimization.

- Design secure, multi-tenant systems with robust isolation and enterprise-grade availability.

- Make architectural trade-offs across performance, reliability, maintainability, and cost.

4. Production Engineering & Platform Reliability

- Own the end-to-end engineering lifecycle, from architecture and implementation to production deployment and ongoing maintenance.

- Establish engineering standards for CI/CD, automated testing, deployment, monitoring, and incident management.

- Implement observability, distributed tracing, performance monitoring, and operational diagnostics.

- Drive system reliability, availability, security, and operational excellence.

- Troubleshoot complex production issues across distributed systems, graph databases, and LLM integrations.

- Continuously improve scalability, response times, resource utilization, and infrastructure costs.