We are looking for a highly skilled and hands-on Senior AI Engineer – Agentic AI & RAG to design and build next-generation AI-powered applications. This role is ideal for an engineer with strong expertise in Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and Python. You will work on building intelligent, production-ready AI solutions that go beyond simple prompt engineering or standalone chatbot implementations. You will contribute to the design and development of end-to-end AI applications involving AI Agents, LLM orchestration, RAG and enterprise search, document ingestion pipelines, vector databases, backend APIs, and integrations with enterprise systems. Title : Senior Agentic AI Engineer

Location:
Remote Work Employment Type: Full-time Exp Range : 3
- 5 years

Key Responsibilities
• Design, develop, and implement end-to-end Generative AI and Agentic AI applications based on business and technical requirements.
• Build scalable AI Agent workflows, including agent orchestration, tool calling, API integrations, and multi-step AI workflows.
• Design and implement RAG and enterprise search solutions for document and knowledge-based applications.
• Build and optimize data ingestion and retrieval pipelines, including document processing, chunking, embeddings, indexing, metadata management, retrieval, re-ranking, and context construction.
• Work with vector databases and embedding models and contribute to designing appropriate data structures and retrieval strategies for efficient search.
• Integrate multiple LLMs and AI services into production applications and select appropriate approaches based on use case, performance, latency, and cost.
• Evaluate and improve AI applications for response quality, relevance, retrieval accuracy, reliability, latency, and overall performance.
• Develop scalable and production-quality Python applications and APIs using FastAPI.
• Write clean, modular,



and maintainable Python code supporting AI Agents, LLM integrations, RAG pipelines, and backend services.
• Apply strong knowledge of OOP, asynchronous programming, APIs, and software engineering principles while developing AI applications.
• Work with SQL and NoSQL databases, caching technologies, and messaging or event-driven systems where required.
• Integrate AI applications with external APIs, enterprise systems, data sources, and cloud services. Required

Skills:
• 3+ years of experience in software engineering, backend development, AI engineering, or related areas.
• Strong hands-on experience building applications using Generative AI and Large Language Models (LLMs).
• Experience building AI Agents, Agentic workflows, or multi-step LLM-powered applications, including tool/API integration and workflow orchestration.
• Strong experience designing and implementing RAG, enterprise search, or retrieval-based applications.
• Hands-on experience with document ingestion, chunking, embeddings, vector search, indexing, retrieval, and context management.
• Experience working with vector databases, embedding models, and semantic search.
• Solid Python programming skills with a solid understanding of OOP and software engineering fundamentals.
• Hands-on experience building backend services and APIs using FastAPI.
• Understanding of asynchronous programming, API development, and scalable backend application design.
• Experience working with SQL and/or NoSQL databases.
• Experience integrating applications with external APIs, AI models, and enterprise systems.




• Hands-on experience with GCP or AWS.
• Strong analytical and problem-solving skills with a good understanding of core programming concepts and scalable system design. Preferred

Skills:
• Experience building and deploying production-grade AI or enterprise AI applications.
• Experience with Docker, containerization, and CI/CD pipelines.
• Experience working with multiple LLM providers and models.
• Exposure to LLM observability, monitoring, and evaluation frameworks.
• Understanding of AI application security and secure API development. About Techolution: Techolution is the world’s leading FEA – Full Enterprise Automation specialist. We are trusted by boards and executive leaders who need AI with real business outcomes. Despite Gen AI, LLMs, and billions in investment, most enterprise AI programs aren't delivering results. Techolution fixes that with BPA 4.0. We take the power of big Tech’s Generic AI and multiply it with our Expert AI stack — resulting in business process automations that follow the same nuances as domain experts do on the job at an unprecedented speed. Our platform has delivered over $900M in AI ROI for our clients in less than a year, all while increasing their AI Adoption by 10x. Our 3 power moves for ROI from AI: 1. Value Finder
- We Identify high-impact AI and automation opportunities in enterprises and build solutions that deliver measurable value in as little as 30 days. 2. 100K Challenge: Work on fast-paced AI initiatives where teams build solutions designed to generate 2× ROI within 100 days. 3. GE LEAP: Contribute to enterprise AI transformation through our partnership with Google, helping scale Gemini-driven solutions across organizations. Visit us @www.techolution.com : To know more about our revolutionary core practices and getting to know in detail about how we enrich the human experience with technology.

📌 Senior AI Engineer (India)
🏢 Techolution
📍 India