AI Engr II

Job description

Job Description

We are seeking a highly skilled AI Engineer II to design, build, deploy, and scale next-generation Generative AI and Agentic AI solutions for enterprise applications. The ideal candidate will have deep expertise in Large Language Models (LLMs), Retrieval Augmented Generation (RAG), agentic frameworks, and AI-driven workflow automation. This role will contribute to the development of intelligent AI agents capable of reasoning, planning, collaborating, and operating within complex enterprise environments.

Your role will also include overseeing, supervising and reviewing tasks performed by team members to ensure effective execution of work; managing end‑to‑end processes and projects for both internal and external clients with responsibility for timely and accurate delivery; issuing clear instructions and directions to team members on tasks to be performed; and mentoring and guiding junior colleagues to support their skill development, professional growth, and overall success

Responsibilities

Key Responsibilities

Develop production-grade Generative AI and Agentic AI applications. Build autonomous and semi-autonomous AI agents that can reason, plan, use tools, and collaborate with other agents. Develop advanced RAG pipelines leveraging vector databases, embeddings, and enterprise data sources. Create multi-step reasoning workflows combining deterministic business logic with LLM-generated reasoning. Implement short-term and long-term memory architectures for persistent contextual interactions.

Design and maintain resilient AI workflows incorporating self-correction, failure recovery, debugging loops, and Human-in-the-Loop (HITL) controls. Integrate LLMs, VLMs, enterprise APIs, databases, and external tools into agent ecosystems. Deploy and manage AI applications across cloud, hybrid, and on-premises environments. Ensure production readiness through monitoring, testing, performance optimization, and governance controls.

Required Technical Skills & Experience

Programming & Software Engineering Strong proficiency in Python. Experience designing and implementing enterprise-grade software solutions. Familiarity with software engineering best practices, version control, MLOps Generative AI & Agentic AI Hands-on production experience with agent orchestration frameworks such as LangGraph, OpenAI Agents SDK, or equivalent.

Deep understanding of foundational agentic design patterns, including: Reflection Tool Use Planning Multi-Agent Collaboration Practical experience with: Function calling Structured outputs Prompt engineering Context window management LLMs & Foundation

• Models Experience building applications using: Large Language Models (LLMs) Vision Language Models (VLMs) Embedding models
• Strong understanding of model capabilities, limitations, and optimization techniques.

AI Workflow Orchestration Proven ability to develop

Self-healing workflows Automated debugging mechanisms Human-in-the-Loop approval processes Quality assurance and audit checkpoints Cloud & Deployment Experience deploying Generative AI solutions in: On-premises environments Hybrid architectures Public cloud environments Hands-on experience in any one of the below cloud platforms : Microsoft Azure AWS Google Cloud Platform (GCP) Data Science & Machine Learning Experience applying data mining and machine learning techniques, including: Decision Trees Neural Networks Support Vector Machines (SVM) Anomaly Detection Recommender Systems Pattern Discovery Text Mining

Qualifications

YOU MUST HAVE 3-6 years experience