Senior GenAI & RAG Platform Engineer

BNY Mellon; Jersey City (NJ); Vor Ort; USD 120.000 - 200.000; Vollzeit

Zusammenfassung

BNY Mellon seeks a senior-level engineer to design, build, and operate production-grade GenAI and Retrieval Augmented Generation (RAG) platforms at scale in Jersey City, NJ. You will industrialize LLM-based systems with guardrails, observability, evaluation frameworks, and cost-conscious operations.

You will own end-to-end lifecycle management, establish CI/CD for ML pipelines, implement telemetry and tracing, and collaborate with governance to ensure reliability and security across the AI

Qualifikationen

• Strong experience building and operating production ML or GenAI systems in enterprise environments.
• Hands-on with LLM orchestration frameworks like LangChain and/or LlamaIndex.
• Experience with model registries and experiment tracking (MLflow or equivalent).
• Solid understanding of Kubernetes-based deployments and cloud-native architectures.
• Familiarity with feature stores, data pipelines, and retriever/index lifecycle management.
• Proven experience implementing telemetry, logging, metrics, and distributed tracing for ML/AI workloads.
• Strong knowledge of CI/CD practices for ML, GenAI, and data-driven systems.

Aufgaben

• Design and build production-ready RAG pipelines with guardrails, tracing, and observability.
• Implement offline and online evaluation frameworks for prompts, models, and datasets.
• Own end-to-end lifecycle management for GenAI systems, including versions and configurations.
• Establish and maintain CI/CD pipelines for prompts, models, and data.
• Implement cost and performance monitoring (tokens, latency, throughput, spend).
• Build and enforce safety mechanisms (content filtering, abuse detection, red-teaming).
• Define and operationalize incident management workflows (alerts, triage, rollback).
• Collaborate with product, platform, and governance teams for reliability, security, compliance.
• Mentor engineers and promote best practices for scalable, trustworthy AI.

Kenntnisse

Production ML systems

LLM orchestration

Kubernetes deployments

CI/CD for ML

Telemetry & tracing

LangChain

LlamaIndex

Model registries & experiment tracking

Tools

MLflow

Jobbeschreibung

BNY Mellon seeks a senior-level engineer to design, build, and operate production-grade GenAI and Retrieval Augmented Generation (RAG) platforms at scale in Jersey City, NJ. You will industrialize LLM-based systems with guardrails, observability, evaluation frameworks, and cost-conscious operations.

You will own end-to-end lifecycle management, establish CI/CD for ML pipelines, implement telemetry and tracing, and collaborate with governance to ensure reliability and security across the AI