Design, develop and deploy enterprise-grade AI solutions, including AI Agents, RAG-based applications, Intelligent Automation workflows and LLM-powered platforms. The candidate will work closely with Architects, Product Owners, Data Engineers, and Business Stakeholders to build scalable, secure, and production-ready AI systems that integrate with enterprise applications and data platforms. This role requires both strong software engineering capabilities and practical expertise in Generative AI technologies.

Responsibilities

- Design and implement autonomous and semi-autonomous AI Agents
- Implement tool calling and function calling capabilities
- Create prompt templates and prompt optimization strategies
- Define agent workflows and state management
- Optimize retrieval accuracy and response quality
- Implement knowledge grounding mechanisms
- Integrate AI solutions with enterprise systems through APIs
- Consume and expose REST APIs
- Work with structured and unstructured data sources
- Build data pipelines for AI applications
- Deploy AI solutions in cloud environments
- Implement CI/CD pipelines for AI applications
- Design and develop AI Agents, RAG applications, and intelligent automation solutions
- Build and optimize agent workflows, prompt strategies, and knowledge retrieval mechanisms
- Develop backend services and APIs using Python, FastAPI, REST APIs, and GraphQL
- Integrate AI solutions with enterprise applications, data platforms, and external systems
- Build and deploy cloud-native AI applications on AWS (Lambda, S3, ECS/EKS)




- Implement CI/CD pipelines and follow software engineering best practices for scalable deployments

What youll bring

- 6-10 years of software engineering experience, including at least 2 years of hands-on AI/Generative AI development experience.
- Strong programming expertise in Python (mandatory) and working knowledge of JavaScript/TypeScript .
- Experience building AI Agents, RAG-based solutions, LLM-powered applications , and other Generative AI solutions.
- Hands-on experience with LangChain, LangGraph , or similar AI orchestration frameworks.
- Strong understanding of RAG architectures, vector databases, embeddings, prompt engineering , and knowledge grounding techniques.
- Experience developing and integrating REST APIs, GraphQL services, and FastAPI-based applications .
- Cloud deployment experience on AWS , including Lambda, S3, ECS, and EKS .
- Familiarity with enterprise integrations, API development, data pipelines , and working with structured and unstructured data sources.
- Knowledge of CI/CD pipelines, containerization, and cloud-native architectures .
- Ability to collaborate effectively with architects, data engineers, product owners, and business stakeholders.
- Robust analytical, problem-solving, and communication skills with a focus on delivering scalable, secure, and production-ready AI solutions.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 AI Engineer (Pune)
🏢 RCG Global Services
📍 Pune