Staff AI Application Engineer
Core
Build production-grade GenAI and Agentic AI backend services for Cyber, Risk, Regulatory, Control & Security domains.
Role type
Staff AI Application Engineer (Individual Contributor)
Builds
Backend services powering autonomous and semi-autonomous AI agents deployed on OpenShift.
Domain
Financial Services / Generative AI / Agentic AI
Deliverable
production ML models | product features
Required skills
Python, Django/FastAPI, Celery, API Security (OAuth2/JWT), Kubernetes/OpenShift, CI/CD, GenAI patterns (RAG, Agents, MCP, A2A), AI Observability (OpenTelemetry, Langfuse, LangSmith)
Preferred skills
PostgreSQL/Redis/Vector DBs, Vue.js/React, LLM providers (OpenAI, Anthropic, Cohere, Llama), Prompt engineering, Monitoring stacks (Grafana, Prometheus)
Technologies
Python, Django, FastAPI, Celery, OpenShift, Kubernetes, LangChain, LangGraph, OpenTelemetry, Langfuse, LangSmith, OAuth2, JWT, GitHub Actions, Jenkins, PostgreSQL, Redis, FAISS, Milvus, Vue.js, React, Grafana, Prometheus
Responsibilities
Build and deploy backend services for Agentic AI applications; Productionize AI prototypes into reliable backend applications; Deploy and operate applications on OpenShift/Kubernetes; Build and maintain secure RESTful APIs; Integrate AI capabilities (RAG, multi-agent systems) and optimize performance; Write unit/integration tests and participate in code reviews; Mentor engineers on backend and productionization best practices.
Seniority
Staff, hands-on IC with mentorship