Agentic AI Developer (Principal / Lead Level)

Role Summary

We are seeking a highly experienced Agentic AI Developer to design, build, evaluate, and optimize complex agentic AI systems for enterprise use cases. This role requires deep hands‑on experience with multi‑agent architectures, strong judgment in model and system design, and the ability to continuously improve AI system performance aligned to business priorities.

This is a hands‑on technical leadership role, not an execution‑only developer position.

Key Responsibilities

Agentic AI System Design & Development

• Design and implement complex multi‑agent workflows using frameworks such as LangChain, LangGraph, CrewAI, Semantic Kernel, or equivalent.
• Architect agent systems that incorporate planning, memory, tool orchestration, feedback loops, and safe control flows.
• Own agent behavior end‑to‑end, from prompt and tool design to runtime execution and iteration.

Evaluation & Performance Optimization

• Define and implement evaluation frameworks for agentic systems, including automated evaluation (e.g., LLM‑as‑judge, metrics) and human‑in‑the‑loop feedback.
• Analyze agent outputs to identify failure modes, inefficiencies, hallucinations, and quality gaps.
• Continuously enhance system performance across accuracy, latency, cost, reliability, and business impact.

Machine Learning & Model Decision‑Making

• Make informed decisions on model selection, architecture, and trade‑offs based on use case, constraints, and business goals.
• Identify model limitations, risks, and loopholes, and proactively mitigate them through design or experimentation.
• Optimize model and system performance based on business priorities, not just technical metrics.

Data & SQL Proficiency

• Use SQL confidently to analyze data, validate outputs, debug issues, and support evaluation and optimization efforts.
• Work independently across data sources without reliance on downstream teams for basic analysis.

Cross‑Functional Collaboration

• Partner closely with product, business, and engineering stakeholders to translate business objectives into robust agentic AI solutions.
• Clearly communicate technical decisions, trade‑offs, and system behavior to both technical and non‑technical audiences.

Required Qualifications

• 8+ years of experience in AI/ML, data science, or backend engineering, with significant hands‑on work in agentic or GenAI systems.
• Proven experience building production‑grade agentic AI systems, not just prototypes or demos.
• Strong understanding of:
• Multi‑agent architectures
• Prompt engineering and agent orchestration
• Evaluation methodologies for LLM and agentic systems
• Demonstrated ability to make independent architectural and model decisions.
• Strong SQL skills for data analysis and debugging.
• Proficiency in Python and modern AI/ML tooling.

Nice to Have

• Experience deploying agentic systems in enterprise or regulated environments.
• Exposure to MLOps, monitoring, and post‑deployment optimization.
• Experience aligning AI system performance with business KPIs.

What This Role Is Not

• Not an entry‑level or learning‑on‑the‑job agentic AI role
• Not an execution‑only LangChain / prompt‑engineering position
• Not a role where architectural decisions are fully prescribed by others