Staff Engineer – Agentic AI
Republic Services · Environmental Services
staff
Salary Range (USD)
Negotiable
Location
USA
Visa Support
Not Supported
Funding Stage
Unknown
Job Responsibilities
- • Own the Agentic AI platform end‑to‑end, including agent orchestration, tool calling, planner/executor, and multi‑agent patterns
- • Ensure enterprise context is reliably available at inference time via retrieval, memory, hybrid search, reranking, and access controls
- • Implement robust LLMOps with evaluations, golden datasets, prompt/agent versioning, tracing, token and cost budgets, and CI/CD for agents
- • Maintain safety in a regulated enterprise environment, handling prompt injection, data exfiltration, PII, human‑in‑the‑loop, and audit logging
Required Skills
7–10+ years building and scaling production systemsRecent hands‑on GenAI/agentic work in productionShipped agents or LLM pipelines at scaleSolid data experience with vector stores, chunking, hybrid search, and retrieval judgmentCloud experience primarily AWS/Bedrock, comfortable with containers and serverlessTrack record of technical leadership and mentoring without a manager title
Engineering Culture & Tech Stack
AWSBedrockcontainersserverlessvector storeshybrid searchLLM
ownership
technical leadership
Raw Post
Show original text
Republic Services | Staff Engineer – Agentic AI | REMOTE (US) | Full-time | $175k is our salary midpoint + 20% target bonus
Republic Services is the second largest environmental services companies in North America — ~40K employees, thousands of trucks, hundreds of facilities, and a mountain of operational data that has never had an AI layer on top of it. We have a backlog of hundreds of Agentic AI ideas that we need to deliver and a foundation of ontologies, evaluations, guardrails, etc... that we need to build.
We're hiring a Staff Engineer now to be the first hire and plan to expand the team aggressively. You will own that platform end to end, not manage the people.
What you'll work on
- Agent orchestration: tool calling, planner/executor and multi-agent patterns, MCP/A2A integrations with enterprise systems
- Making enterprise context reliably available at inference time — retrieval, memory, hybrid search, reranking, access controls
- LLMOps that isn't hand-wavy: evals and golden datasets, prompt/agent versioning, tracing, token and cost budgets, CI/CD for agents
- Safety in a regulated enterprise: prompt injection, data exfiltration, PII handling, human-in-the-loop, audit logging
You should have
- 7–10+ years building and scaling production systems, with recent, hands-on GenAI/agentic work in production (not just demos)
- Shipped agents or LLM pipelines at scale
- Solid data chops — vector stores, chunking, hybrid search, knowing when retrieval is the wrong answer
- Cloud experience (we're primarily AWS / Bedrock); comfortable with both containers and serverless
- Track record of technical leadership and mentoring without needing a manager title
Nice to have: LangGraph / Semantic Kernel / PydanticAI, GraphRAG, knowledge graphs, LangFuse/LangSmith, multimodal.
Comp & benefits: $175k is our midpoint for salary + 20% annual target bonus, 401(k) with company match, ESPP, medical/dental/vision, PTO. Remote eligible, prefer AZ timezones +/-1. Not sponsorship eligible.
Why you should want to work here: We build cool stuff
email me (jgardner@republicservices.com) directly with the most interesting agent you've shipped.
AI Risk Insights
No major risk signals detected.
Recent News
No recent updates
Data Source
Content parsed by LLM from Hacker News raw data. Confidence:HIGH