Lead design and delivery of enterprise-grade UI and backend services using ReactJS and Java/Spring Boot.Drive microservices architecture, API design, and integration patterns across a complex enterprise ecosystem.Own end-to-end delivery across SDLC: requirements, design, development, testing, deployment, and production support.Establish and enforce engineering best practices for code quality, automated testing, CI/CD, and DevOps.Optimize system performance for high-volume, real-time, latency-sensitive workflows.
Design and build LLM-powered applications using Python for enterprise use cases (e.g., agent assist, summarization, knowledge retrieval, workflow automation).Implement RAG solutions (embeddings + retrieval + vector search) tuned for relevance, latency, and reliability.Build agentic workflows and tool-using patterns using frameworks such as LangChain / LangGraph (or equivalent orchestration approaches).Define and drive AI quality practices including evaluation, monitoring signals, accuracy tuning, and continuous improvement loops.Support LLM stack upgrades and AI platform evolution aligned to roadmap and operational requirements.Integrate GenAI services into platform workflows via well-designed APIs, service interfaces, and security/compliance-aligned patterns.
Production Reliability & Operational Excellence
Own production stability for both platform and AI components; lead incident triage, root cause analysis, and preventative fixes.Drive observability improvements across systems: monitoring, logging, alerting, and reliability metrics for critical workflows.Ensure operational readiness for releases, peak events, and production rollouts.
Manage, mentor, and develop engineers through coaching, feedback, and technical guidance.Build a culture of ownership, accountability, and engineering excellence.Support hiring and onboarding for blended platform + GenAI talent.