Description

Design, build, and own production-grade Agentic AI systems, including LLM agent architectures, tool orchestration, and secure integrations.

This role is on-site.

Responsibilities

• Architect and implement multi-step reasoning, planner/executor patterns, and tool orchestration for AI agents.
• Build secure tool integrations with robust guardrails, approval workflows, and reliability patterns like retries and idempotency.
• Develop reusable agent frameworks, SDKs, evaluation pipelines, RAG systems, and memory modules.
• Manage production LLMOps, including inference services, CI/CD pipelines, observability, and cost/performance optimization.
• Embed security, privacy, and Responsible AI controls such as least-privilege access, PII handling, and prompt injection defenses.

Required Skills

• 8+ years of software engineering experience with strong Python skills.
• Hands-on experience building and deploying LLM agents or tool-using AI systems.
• Production backend and distributed systems experience.
• Experience with RAG, agent evaluation, and observability tools.
• Proficiency with cloud platforms: AWS, Azure, or GCP.
• Experience with CI/CD practices for AI systems.
• Knowledge of LangGraph or similar agent orchestration frameworks.

Preferred Skills

• Experience with secure, reliable production AI systems at scale.
• Bachelor's degree in Computer Science or related field.

Key Skills

Education

Bachelor's degree