Lead AI Engineer – Generative AI & RAG

We are seeking an experienced Lead AI Engineer to design, develop, and deploy enterprise-grade AI applications using Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and enterprise APIs.

The ideal candidate will have strong hands-on experience building production-ready AI solutions, developing RAG pipelines, integrating LLMs with enterprise systems, and deploying AI applications across cloud and on-premises environments.

This role requires a combination of technical expertise, solution architecture, engineering leadership, and collaboration with business stakeholders. The selected candidate will help develop AI-powered assistants that support frontline employees by answering customer questions, retrieving relevant product information, and providing recommendations to improve customer service and sales.

Key Responsibilities

• AI Application Development: Design, develop, and maintain enterprise AI applications using Python, LLMs, and enterprise APIs.
• RAG Pipeline Development: Build, optimize, and maintain Retrieval-Augmented Generation pipelines, including document ingestion, chunking, embeddings, retrieval, and vector search.
• LLM Integration: Integrate large language models with enterprise systems, internal knowledge sources, and business applications.
• AI Performance Optimization: Evaluate AI-generated responses for accuracy, relevance, reliability, latency, and cost-effectiveness.
• AI Evaluation & Troubleshooting: Identify and resolve issues related to model performance, retrieval quality, hallucinations, and application reliability.
• Deployment & Operations: Deploy, monitor, and maintain AI services in cloud and on-premises environments while ensuring security, scalability, and operational stability.
• Solution Architecture: Lead technical discussions and contribute to architecture decisions for scalable, secure, and maintainable AI solutions.
• Code Reviews & Mentoring: Review code, establish engineering best practices, and mentor engineers on AI implementation and application development.
• Stakeholder Collaboration: Work closely with business stakeholders and cross-functional teams to understand requirements, prioritize development tasks, and demonstrate project progress.
• Documentation: Maintain technical documentation, deployment runbooks, architecture specifications, and knowledge transfer materials.
• Continuous Improvement: Identify opportunities to improve AI workflows, model performance, system observability, and overall solution quality.

Required Qualifications & Skills

1. Python & API Development

• 5+ years of professional experience developing applications using Python.
• 3+ years of experience designing and building production-grade REST APIs.
• Strong understanding of application architecture, API integration, and software engineering best practices.

2. Generative AI, LLMs & RAG

• 2+ years of experience developing applications powered by Large Language Models (LLMs).
• At least 1+ year of hands-on experience implementing RAG solutions.
• Strong experience with embeddings, vector databases, document ingestion, and semantic search.
• Ability to develop and optimize AI-powered applications that retrieve relevant information from enterprise knowledge sources.

3. Solution Architecture & Cloud Deployment

• 2+ years of experience leading solution architecture and engineering delivery.
• 3+ years of experience deploying applications on cloud infrastructure.
• Experience designing scalable, reliable, and secure enterprise applications.

Preferred Qualifications

• Experience with AI workflow orchestration and agent-based AI solutions.
• Experience fine-tuning models and working with open-source LLMs.
• Familiarity with PyTorch or similar machine learning frameworks.
• Experience implementing AI evaluation frameworks, observability, monitoring, and guardrails.
• Knowledge of prompt engineering, hallucination mitigation, and responsible AI practices.
• Experience deploying AI services in cloud and on-premises environments.
• Experience integrating AI applications with enterprise APIs and internal knowledge repositories.