Description

Key Responsibilities

• Design and implement AI Agent architectures (planner/executor, multi-step reasoning, tool orchestration)
• Build secure tool integrations, guardrails, approvals, and reliability patterns (retries, fallbacks, idempotency)
• Develop reusable agent frameworks, SDKs, evaluation pipelines, RAG, and memory systems
• Own production LLMOps: inference services, CI/CD, observability, and cost/performance optimization
• Embed security, privacy, and Responsible AI controls (least-privilege access, PII handling, prompt injection defenses, audit trails)
• Provide technical leadership and collaborate cross-functionally

Required Qualifications:

• 5–8+ years software engineering experience
• Hands-on experience building and deploying LLM agents or tool-using AI systems
• Strong Python skills and production backend/distributed systems experience
• Experience with RAG, agent evaluation, observability, and cloud platforms (AWS/Azure/GCP)
• Proven ability to deliver secure, reliable production AI systems

Key Skills

Education

Bachelor's degree