Manager, GenAI L3 Support Engineer, Group Technology & Ops
Core
Own L3 incident response for GenAI use cases in production, triaging, debugging, and fixing defects to ensure reliability.
Role type
Senior L3 Support Engineer (GenAI)
Builds
GenAI use case pipelines, RAG systems, and safety layers for production environments.
Domain
Financial Services / Generative AI
Deliverable
production ML models
Required skills
Python, LangChain, Elasticsearch, Redis, Guardrails AI, Jenkins, OpenTelemetry, Prometheus, Grafana, Git, Kubernetes, vLLM
Preferred skills
FastAPI, Flask, async patterns, NVIDIA Enterprise AI services
Responsibilities
Triage and resolve complex bugs in LangChain flows and safety layers; Implement safe changes and hotfixes via Jenkins; Harden use case pipelines with validation and circuit breakers; Improve RAG quality by tuning retrieval parameters; Maintain runbooks and playbooks; Drive observability with OpenTelemetry and Grafana; Manage production hygiene including SLOs and SLAs; Coordinate with infra teams on OpenShift and GPU services; Perform safe data operations and PII redaction; Lead blameless post-incident reviews.
Seniority
Senior, hands-on IC
