Generative AI Engineer

Role Overview

We are looking for skilled Generative AI Engineers to create, develop, and deploy sophisticated AI systems. The position focuses on designing RAG (Retrieval-Augmented Generation) pipelines, developing multi-agent frameworks, and embedding AI solutions within enterprise infrastructures. Responsibilities include managing the entire technical delivery process from initial prototypes through to production releases, ensuring systems are scalable, reliable, and performant.

Key Responsibilities

• Develop custom Agentic AI solutions and orchestrate multi-agent workflows.
• Integrate AI core models seamlessly into client operational environments.
• Manage technical delivery for diverse deployments, covering early prototypes to stable production versions.
• Conduct debugging, root cause analysis, and optimize latency and prompt handling.
• Implement best practices for large language model (LLM) evaluation, including guardrails and version management.
• Collaborate closely with product teams and client stakeholders to achieve KPI-focused goals.
• Identify and communicate risks early, such as model drift, data leakage, and system reliability issues.
• Contribute insights towards product roadmaps, deployment design, and reusable component frameworks.

Mandatory Skills

• Proficiency in Generative AI ecosystem technologies including RAG pipelines, multi-agent architectures, LangChain, LangGraph, and LlamaIndex.
• Experience with Model Context Protocols (MCP), Agent-to-Agent (A2A) protocols, and the Agent Developer Kit (ADK).
• Expertise in LLM engineering such as prompt engineering, fine-tuning methods, and model evaluation techniques.
• Hands-on experience with data science tools, including Python, pandas, scikit-learn, and PyTorch.
• Exposure to cloud platforms and MLOps including AWS, Azure, and GCP.
• Familiarity with DevOps tools such as Docker, Kubernetes, Terraform, CI/CD pipelines, GitHub Actions, GitLab, Jenkins, CircleCI, and GitOps practices.
• Backend development skills with Python as mandatory, alongside JavaScript or TypeScript for API integrations.

Preferred Experience and Qualifications

• Background working directly with customers on technical deployments.
• Degree in Computer Science, Engineering, Statistics, or a related quantitative field.
• Strong communication capabilities for articulating technical details to varied audiences.
• Proven track record of delivering complex AI systems efficiently under ambiguous and fast-paced conditions.

Interview Information

• Interview Format: Face-to-face (F2F)
• Date Scheduled: 19th September 2026
• Interview Locations: Bangalore and Hyderabad

Eligibility

Candidates holding a B.Sc in any specialization or B.Tech/B.E. degrees in any specialization are eligible to apply.

Additional Information

This is a walk-in interview opportunity hosted by Platlap Solutions, a leading IT company based in Hyderabad, India. The annual salary range offered for this role is between 600000 and 850000 INR.