Overview

Primary Responsibilities: • Design, develop, and deploy Agentic AI solutions using LLMs, tools, memory, orchestration, and multi-step reasoning workflows • Build and maintain RAG-based applications using vector databases, embeddings, document ingestion pipelines, retrieval strategies, and prompt engineering • Develop AI-powered workflow automation solutions to improve operation

Responsibilities

• Design, develop, and deploy Agentic AI solutions using LLMs, tools, memory, orchestration, and multi-step reasoning workflows
• Build and maintain RAG-based applications using vector databases, embeddings, document ingestion pipelines, retrieval strategies, and prompt engineering
• Develop AI-powered workflow automation solutions to improve operational efficiency and business process intelligence
• Work with frameworks such as Spring AI, LangChain, LangGraph, and related AI orchestration tools
• Integrate AI capabilities into enterprise applications, APIs, microservices, and cloud-native platforms
• Build scalable backend services using Java/Spring Boot and/or Python-based AI frameworks
• Implement prompt engineering, evaluation, guardrails, observability, and monitoring for AI applications
• Work with cloud services on AWS and/or Azure, including AI/ML services, storage, compute, serverless, containerization, and deployment pipelines
• Collaborate with product owners, architects, data engineers, and business stakeholders to understand requirements and deliver AI solutions
• Explore and evaluate emerging AI tools, LLM providers, model APIs, and open-source frameworks
• Ensure AI solutions follow security, compliance, privacy, and responsible-AI best practices

Qualifications

• Bachelor's or Master's degree in Computer Science, Engineering, Data Science, AI/ML, or a related field
• 3+ years of software engineering experience, with hands-on work building AI/GenAI or LLM-based applications (e.g., agentic solutions, RAG systems, or AI chatbots)
• Practical experience integrating LLMs via APIs (e.g., OpenAI, Azure OpenAI, Anthropic, Amazon Bedrock, or open-source models)
• Working experience with at least one GenAI framework such as Spring AI, LangChain, or LangGraph
• Hands-on cloud experience with AWS or Azure (compute, storage, and AI/ML services)
• Solid programming skills in Java/Spring Boot and/or Python
• Understanding of RAG fundamentals: embeddings, chunking, retrieval, vector search, and prompt engineering
• Working knowledge of agentic concepts: tool/function calling, orchestration, memory, and multi-step reasoning workflows
• Solid understanding of REST APIs and microservices
• Familiarity with Git, CI/CD pipelines, and Docker
• Proven solid problem-solving skills and the ability to build reliable, maintainable, production-grade systems
• Awareness of security, privacy, and responsible-AI practices when building AI applications
• Exposure to model fine-tuning, prompt evaluation frameworks, or synthetic data generation
• Advanced RAG techniques such as re-ranking, hybrid search, and advanced document ingestion pipelines
• Multi-agent workflows and autonomous task execution
• Knowledge of LLM evaluation, hallucination reduction, grounding, tracing, and guardrails
• Knowledge of observability tools (e.g., Splunk, Dynatrace, Amazon CloudWatch, Azure Loginsights) for monitoring applications and AI systems
• Familiarity with event-driven architecture, message queues, and enterprise integration patterns
• Familiarity with governance, access control, and compliance requirements for GenAI applications