AI Engineer

We are looking for an experienced AI Engineer to design, develop, and deploy advanced Agentic AI solutions that automate complex business processes. The ideal candidate will have strong expertise in LangGraph, LangChain, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and multi-agent architectures. You will work closely with cross-functional teams to build scalable, production-grade AI applications, develop intelligent workflows, optimize AI system performance, and contribute to enterprise AI governance and responsible AI practices. This role requires a strong software engineering foundation, hands-on experience with modern AI frameworks, and the ability to deliver robust AI solutions in a fast-paced environment. Key Responsibilities Design, develop, and implement agentic AI solutions using LangGraph and LangChain. Build and manage multi-step AI workflows with tool integration, memory management, routing, and guardrails. Integrate and operationalize LLMs using AWS Bedrock, OpenAI, Azure OpenAI, or similar platforms. Develop prompt engineering strategies, orchestration frameworks, evaluation systems, and optimization techniques. Architect and implement multi-agent systems using planner, executor, critic, and reflection patterns. Design and deploy scalable RAG pipelines, including embeddings, vector databases, retrieval tuning, and citation generation. Develop backend services and APIs using Python and FastAPI. Ensure application reliability through testing, code reviews, CI/CD pipelines, and performance monitoring. Collaborate with product, engineering, and business teams to deliver AI-powered solutions. Implement AI governance, security controls, and responsible AI best practices. Optimize AI system scalability, performance, and operational efficiency. Support cloud-native AI deployments and enterprise-scale AI initiatives. Key Skills and Qualifications 6–10 years of experience in AI/ML Engineering, Software Development, or related domains. Strong hands-on experience with LangGraph, LangChain, and Agentic AI frameworks. Expertise in integrating and deploying LLMs using AWS Bedrock, OpenAI, Azure OpenAI, or similar platforms. Proven experience in designing multi-agent AI architectures with planning, execution, reflection, and human-in-the-loop workflows. Strong experience building and optimizing Retrieval-Augmented Generation (RAG) solutions. Proficiency in Python (3.10+) and FastAPI or similar backend frameworks. Solid understanding of software engineering best practices, modular architecture, code quality, and maintainability. Experience with Pytest, automated testing, mocking, contract testing, and CI/CD quality processes. Strong problem-solving, analytical, and communication skills. Experience with AWS services such as S3, Glue, Lambda, Step Functions, Kinesis, Redshift, and Athena is preferred. Knowledge of PostgreSQL/RDS, query optimization, migrations, and database performance tuning. Familiarity with asynchronous programming (asyncio, aiohttp, httpx), concurrency patterns, retries, and timeout handling. Experience with Docker, ECS/EKS, Infrastructure as Code (IaC), and cloud-native deployments. Understanding of AI Governance, Data Governance, Responsible AI, and enterprise compliance frameworks. Ability to thrive in a collaborative and fast-paced work environment. Location : Pune,Bangalore Apply by sending your CV to careers@cliqhr.co.in