Artificial Intelligence Engineer

About the Role -

We are seeking an experienced AI Engineer with strong hands-on expertise in Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI. The ideal candidate will design, develop, integrate, and deploy AI-powered applications using Python, modern AI/ML frameworks, cloud AI services, APIs, and scalable backend architectures.

This role is highly hands-on and requires the ability to take AI solutions from concept and prototype through production. You will work closely with engineering, product, data, and other cross-functional teams to deliver reliable, measurable, and secure AI capabilities.

Key Responsibilities -

• Design, develop, test, deploy, and maintain production-grade AI/ML and Generative AI applications using Python.
• Build solutions using Large Language Models (LLMs), including prompt engineering, model selection, evaluation, optimization, and integration.
• Design and implement Retrieval-Augmented Generation (RAG) solutions using embeddings, vector databases, document processing, retrieval, reranking, and grounded generation.
• Design and develop Agentic AI solutions, including autonomous or semi-autonomous agents, tool use, planning, memory, workflows, and multi-agent orchestration.
• Build and integrate AI agents with enterprise systems, APIs, databases, and business workflows.
• Evaluate and implement AI/ML frameworks and orchestration technologies such as LangChain, LangGraph, or equivalent platforms.
• Develop RESTful APIs and scalable backend services to expose AI capabilities to applications and enterprise users.
• Integrate commercial and open-source AI models and cloud AI services such as OpenAI, Azure AI, AWS, Google Cloud, Hugging Face, or equivalent platforms.
• Design AI solutions with appropriate security, privacy, access controls, observability, reliability, latency, and cost considerations.
• Develop evaluation frameworks and monitoring approaches to measure accuracy, relevance, hallucination, latency, quality, and business outcomes of AI applications.
• Collaborate with product managers, software engineers, data teams, and business stakeholders to translate requirements into practical AI solutions.
• Troubleshoot and optimize AI applications in production and contribute to continuous improvement of models, prompts, retrieval pipelines, and agent workflows.
• Stay current with advances in Generative AI, LLMs, Agentic AI, RAG, AI infrastructure, and responsible AI practices, and recommend technologies that can create business value.
• Mentor junior engineers and contribute to engineering standards, architecture decisions, documentation, and knowledge sharing.

Technical Skills-

• AI & Generative AI: Generative AI, LLMs, Agentic AI, RAG
• Programming: Python
• AI Frameworks: LangChain, LangGraph, LlamaIndex / Semantic Kernel
• LLM & RAG: Prompt Engineering, Embeddings, Vector Search, Reranking
• AI Agents: Tool/Function Calling, Agent Workflows, Memory, Multi-Agent Systems, MCP
• APIs & Backend: REST APIs, Microservices, API/SDK Integration
• Databases: PostgreSQL, SQL/NoSQL, Vector Databases (Pinecone, Qdrant, pgvector)
• Cloud: AWS / Azure / GCP, OpenAI, Azure AI, Hugging Face
• DevOps: Docker, Kubernetes, CI/CD
• AI Operations: LLMOps/MLOps, AI Evaluation, Monitoring, Observability

What We are looking for -

• Strong ownership and accountability for delivering reliable, scalable, and production-ready AI solutions.
• Solid understanding of Generative AI, LLMs, RAG, Agentic AI, and AI application architecture.
• Ability to translate business requirements into practical and maintainable AI solutions.
• Strong problem-solving skills with a focus on accuracy, performance, scalability, security, and cost optimization.
• Hands-on experience taking AI solutions from prototype to production, including testing, deployment, monitoring, and optimization.
• Strong communication and collaboration skills, with the ability to work effectively with engineering, product, data, and business teams.
• Willingness to learn and contribute to the rapidly evolving AI/LLM ecosystem and AI engineering practices.