Agentic AI Engineer

Guarav Sidharth; United States; Remote; USD 120,000 - 240,000; Full time

Job summary

Guarav Sidharth is seeking an AI Engineer to build production-grade agentic AI for Fortune 500 enterprises across CPG, Banking, MedTech and Industrial. You’ll own a full slice of a client engagement, from agent design to production, and stand behind the results.

Responsibilities include designing agentic workflows, tooling and orchestration, shipping reliable code in Fortune 500 production environments, building eval harnesses, and leading technical sessions with client engineers and product

Qualifications

• 3-10 years in software engineering, with at least one system taken to production and owned.
• Hands-on LLM experience: multi-agent orchestration, RAG, tool-calling, prompt design.
• Strong Python, plus testing, code review, deployment and monitoring.
• Experience designing evals or test strategies for non-deterministic systems.
• Comfortable with ambiguous requirements; can drive work to a reliable outcome independently.
• Clear, credible communicator with client engineers.

Responsibilities

• Design agentic workflows: agent topology, tool design, orchestration
• Ship reliable, well-tested agentic code in Fortune 500 production environments
• Build eval harnesses and rubrics to hit a 99.99% reliability bar
• Lead technical sessions with client engineers and product owners
• Review L1 engineers code and mentor them toward workstream ownership

Skills

Production experience

LLM experience

Python

Testing

Code review

Deployment

Monitoring

Eval design

Adaptability

Communication

Tools

Azure

AWS

Databricks

SAP

Oracle

Snowflake

Job description

Role & responsibilities

Build production-grade agentic AI for Fortune 500 enterprises across CPG, Banking, MedTech and Industrial. As an AI Engineer, youll own a full slice of a client engagement, from agent design to production, and stand behind the results.

• Design agentic workflows: agent topology, tool design, orchestration
• Ship reliable, well-tested agentic code in Fortune 500 production environments
• Build eval harnesses and rubrics to hit a 99.99% reliability bar
• Lead technical sessions with client engineers and product owners
• Review L1 engineers code and mentor them toward workstream ownership

Preferred candidate profile

• 3-10 years in software engineering, with at least one system taken to production and owned
• Hands‑on LLM experience: multi‑agent orchestration, RAG, tool‑calling, prompt design
• Strong Python, plus testing, code review, deployment and monitoring
• Experience designing evals or test strategies for non‑deterministic systems
• Comfortable with ambiguous requirements; can drive work to a reliable outcome independently
• Clear, credible communicator with client engineers

Good to have

• Production experience on Azure, AWS or Databricks
• Exposure to SAP, Oracle or Snowflake
• Experience in banking, MedTech, CPG or industrial domains
• Client‑facing or consulting delivery experience
• Contributions to agentic tooling, open source or eval frameworks