Generative AI Engineer

Role Overview

We are seeking an

AI Solutions Engineer

with strong expertise in

Generative AI, Large Language Models (LLMs), and full-stack development

to design, build, and deploy AI-powered applications. This role involves end-to-end solution delivery, from identifying high-impact AI use cases to implementing production-ready systems integrated with enterprise applications and cloud platforms.

Key Responsibilities

• Collaborate with business teams to identify high-value AI opportunities.
• Design and implement AI workflows using LLMs, Retrieval-Augmented Generation (RAG), agent-based architectures, or prompt chaining.
• Prototype and deliver solutions using platforms such as OpenAI, Azure OpenAI, Claude, Gemini, or similar.
• Apply modern AI solution patterns (e.g., RAG pipelines, multi-agent frameworks, lightweight LLM apps).
• Develop APIs, middleware, and front-end applications to embed AI into enterprise systems.
• Work with vector databases (Pinecone, FAISS, Weaviate) for semantic search and knowledge retrieval.
• Design scalable and secure solutions aligned with cloud and enterprise architecture standards.
• Build intuitive front-end interfaces (React, , or similar) for AI-driven applications.
• Develop robust back-end services , Python, FastAPI, etc.) to orchestrate AI pipelines.
• Ensure secure authentication, role-based access, and seamless user experiences.
• Create, test, and refine prompts for LLMs.
• Implement few-shot, chain-of-thought reasoning, and function-calling techniques to enhance reliability and accuracy.
• Use frameworks like LangChain, LlamaIndex, Semantic Kernel, or similar for orchestration.
• Build modular and composable pipelines for AI solution development.
• Establish evaluation frameworks using metrics such as accuracy, hallucination rate, and latency.
• Monitor production performance and implement iterative improvements based on feedback.
• Deploy AI solutions on cloud platforms (AWS, Azure, GCP).
• Use containerization (Docker) and orchestration (Kubernetes) for scalability and resilience.
• Apply DevOps / MLOps practices including CI / CD pipelines, observability, and automated monitoring.
• Document AI workflows, system integrations, and reusable components.
• Promote best practices, reusable templates, and standardized patterns across teams.
• Share knowledge, conduct training, and contribute to organizational AI maturity.

Qualifications & Skills