AI Engineer (GenAI & Agentic Systems)

Overview

Design, prototype and develop generative AI and agent-based automations.

Responsibilities

• GenAI POC and MVP Development
• Design and implement GenAI‐powered automations using LLMs/SLMs, tools, and agents.
• Inference Pipelines for GenAI
• Design and build GenAI inference pipelines that:
• Accept structured and unstructured inputs.
• Apply prompt templates and system instructions.
• Invoke LLMs and tools.
• Postprocess outputs into reliable, auditable results.
• Support real‐time, batch, and asynchronous inference patterns.
• Prompt Engineering & Feature Engineering (Data)
• Design and test prompt templates for data.
• Implement data feature engineering for GenAI.
• Agentic Architecture & Tool Integration
• Design and prototype/develop agentic automations that decompose tasks, plan and reason oversteps, invoke tools and APIs, and handle errors and retries.
• Integrate agents with AI platform and other source APIs.
• Apply guardrails to control agent autonomy, cost, and risk.
• Evaluation of SaaS / COTS GenAI Capabilities
• Technically evaluate GenAI and agentic features embedded in third‐party SaaS/COTS products, including:
• LLM, SLM usage patterns and limitations.
• Prompt and agent customization options.
• API accessibility and automation readiness.
• Observability and audit controls.
• Provide technical input to architecture, procurement, and governance decisions.

Qualifications

• Technical Skills
• Strong proficiency in Python and API‐based service development.
• Hands‐on experience with LLMs, SLMs, RAG, prompt engineering, and Agentic AI frameworks or patterns.
• Strong understanding of API‐first and event‐driven architectures.
• Conceptual & System Skills
• Deep understanding of GenAI inference vs traditional deterministic systems, prompt‐centric and context‐centric design, and agent autonomy vs control tradeoffs.
• Ability to translate experimentation into reliable, automated AI systems.
• Strong collaboration skills across engineering, product, data, and governance teams.
• Familiarity with:
• Vector databases and document retrieval systems.
• Cost and latency optimization for LLMs and SLMs.
• Monitoring and evaluation of GenAI outputs.
• Exposure to AI risk management or responsible AI practices.