Staff Engineer - Agentic AI

vibehackers · United States

$133K to $182K a year as published by the employer

Apply on company site Save to your job tracker Find similar jobs

Applications are completed on the employer's own site.

Summary

Design, build, and operate a large-scale agentic AI platform providing technical leadership and mentorship to engineers.

About this role

# Staff Engineer - Agentic AI

Republic Services

AI/ML & Data

United States

$132k - $182k

Yesterday

💻 Open Source🔥 Hot

Apply →

Deeply focused on GenAI/agent engineering—heavy on prompt/context engineering, agent frameworks, and LLMOps; building production AI platforms and tooling.

## About the Role

Staff Engineer - GenAI responsible for designing, building, and operating a large-scale agentic AI platform that enables autonomous, LLM-driven solutions across the enterprise. Provide hands-on technical leadership, drive GenAI architecture, LLMOps practices, and mentor engineers to produce scalable, secure, and production-ready agentic systems.

## Job Description

## Role

The Staff Engineer - GenAI is a hands-on technical leader responsible for designing, building, and maintaining an enterprise-scale agentic AI platform. The role focuses on architecting LLM-driven systems, enabling autonomous multi-step agent behaviors, ensuring scalability, availability, security, and alignment with enterprise architecture and compliance standards.

## Key Responsibilities

* Own end-to-end development of the Agentic AI platform: design, develop, test, and deploy generative AI capabilities and agent frameworks to support autonomous task execution. * Provide technical direction across the organization and collaborate with solution and enterprise architects to integrate LLMs, agent frameworks, and AI services into broader systems while meeting non-functional requirements (security, scalability, resilience, token economics, latency). * Lead coding standards, prompt engineering, and context engineering best practices; conduct code, prompt, and context-pipeline reviews and establish reproducible experiment/versioning practices (e.g., Git and LLMOps tools). * Build frameworks and orchestration pipelines to integrate LLMs and agents with enterprise data sources, leveraging GenAI tools and protocols (MCP, A2A, function/tool calling) and designing retrieval, memory, and tool-use patterns for reliable inference-time context. * Drive LLMOps/GenAI Ops practices: automated evaluation, prompt/agent/versioning, online/offline evals, observability (traces, token usage, hallucination/grounding metrics), guardrails, CI/CD for prompts/agents/models, and evaluate tools like LangSmith, LangFuse, Bedrock, or cloud AI services. * Mentor and coach engineers in GenAI and software engineering techniques; contribute non-managerial feedback on hiring and promotions.

## Requirements

* 7–10+ years building and scaling enterprise software systems, with substantial experience (10+ years overall and ideally 2+ years focused on GenAI/LLM or software architecture initiatives). * Deep understanding of generative AI and transformer models (examples: Claude, GPT) and practical experience integrating LLMs into enterprise apps, including prompt engineering, context engineering, RAG/GraphRAG, and agentic patterns (ReAct, planner/executor, multi-agent orchestration). * Proficiency with GenAI frameworks/libraries (e.g., LangChain, LangGraph, Semantic Kernel) and familiarity with model-serving runtimes and agent orchestration frameworks. * Cloud and deployment experience (AWS Bedrock, kore.ai, GCP AI) and knowledge of containerization and serverless architectures for scalable agent deployments. * Strong data engineering skills for AI-ready data: chunking, enrichment, governance, vector databases (pgvector, Elastic Search), hybrid search, reranking, knowledge graphs, embeddings, semantic layers, and access controls. * Experience with LLMOps/AI DevOps practices: CI/CD for prompts and agents, eval-driven development, versioning, observability/tracing, cost/token monitoring, automated red-teaming, and guardrail enforcement. * Demonstrated technical leadership, mentorship, communication skills, and a strong focus on AI ethics, safety, privacy, and compliance (prompt injection mitigation, PII handling, audit logging). * Bachelor’s degree in Computer Science or Data Science preferred.

## Compensation & Other Notes

* Pay range: $132,600 - $182,250 USD (DOE). * Eligible for a target annual bonus of 20% of base salary. * Position is not eligible for sponsorship.

### Tech Stack

ClaudeGPTLangChainLangGraphSemantic KernelLangSmithLangFuseBedrockAWS Bedrockkore.aiGCP AIpgvectorElastic SearchSplunkCloudWatchGitMCPA2Afunction/tool callingGraphRAGReAct

### Skills

Technical LeadershipSystem DesignPrompt EngineeringContext EngineeringLLMOps / GenAI OpsObservabilityArchitectureCloud ArchitectureData EngineeringRetrieval & RAGMentorshipCode Quality & TestingVersion ControlExperimentation & EvaluationSecurity, Privacy & ComplianceCommunicationProblem Solving

### Experience Level

Staff/Principal

### Salary

USD 132,600 - 182,250/year

### Employment Type

Full Time

### Benefits

* •Comprehensive medical benefits * •Dental coverage * •Vision coverage * •Health care and dependent care spending accounts * •Short- and long-term disability * •Life insurance and accidental death & dismemberment insurance * •Employee and Family Assistance Program (EAP) * •Employee discount programs * •Retirement plan with generous company match * •Employee Stock Purchase Plan (ESPP) * •Paid Time Off (PTO) * •Washington PTO * •Target annual bonus (20% of base)

Skills named in this posting

and 16 more

About vibehackers

Vibehackers is a global community connecting top talent with innovative companies for remote opportunities.

Similar Staff Engineer - Agentic AI jobs