Job Title: AI Engineer Generative AI, RAG & Agentic AI Experience: 612 Years Remote Key Roles and Responsibilities Design, develop, and deploy enterprise-grade Generative AI applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI architectures. Build end-to-end RAG pipelines, including document ingestion, parsing, preprocessing, chunking, embedding generation, vector indexing, retrieval, reranking, and context-grounded response generation. Develop automated document-processing pipelines to extract and normalize information from PDFs, Word documents, Excel workbooks, scanned files, tables, forms, and other structured and unstructured data sources. Implement OCR, layout detection, table extraction, schema mapping, and data validation to handle heterogeneous document formats, complex tables, merged cells, multi-level headers, and inconsistent data structures. Design and optimize vector search, keyword search, hybrid retrieval, metadata filtering, query rewriting, semantic search, and reranking strategies to improve retrieval accuracy and relevance. Develop prompt engineering strategies, structured outputs, function calling, and context-management techniques to improve LLM response quality, consistency, and reliability. Evaluate and select appropriate LLMs and embedding models based on accuracy, reasoning capabilities, context-window size, latency, throughput, cost, security, and deployment requirements. Implement LLM application tracing, evaluation, and observability using LangSmith or equivalent tools to monitor prompts, model calls, retrieval operations, tool executions, latency, token usage, and errors. Use MLflow or equivalent platforms for experiment tracking, evaluation management, configuration comparison, artifact versioning, and reproducible AI development workflows. Develop evaluation datasets and automated testing pipelines to measure answer correctness, faithfulness, contextual relevance, retrieval performance, citation accuracy, and structured-output validity. Identify and mitigate LLM hallucinations through evidence-grounded generation, source validation, citation verification, confidence-based controls, deterministic validation, and abstention mechanisms. Design and implement Agentic AI workflows using LangGraph, LangChain, LlamaIndex, or similar frameworks to integrate LLMs with APIs, databases, enterprise tools, and business processes. Implement agent orchestration, workflow routing, state management, tool calling, retries, error handling, and human-in-the-loop approval mechanisms where required. Develop scalable backend services and AI APIs using Python, FastAPI, REST APIs, and related technologies to integrate AI capabilities into enterprise applications. Optimize AI application performance, including retrieval quality, inference latency, token consumption, throughput, caching, concurrency, and overall operational cost. Deploy and maintain AI applications on cloud platforms such as Microsoft Azure, AWS, or Google Cloud, using Docker, Kubernetes, CI/CD pipelines, and appropriate deployment practices. Implement security controls, authentication, authorization, data privacy, prompt injection protection, sensitive-data handling, audit logging, and responsible AI practices. Monitor production AI applications, investigate quality degradation and failures, perform root-cause analysis, and implement continuous improvement through evaluation results and user feedback. Collaborate with data engineers, ML engineers, architects, DevOps teams, and business stakeholders to translate requirements into scalable, secure, and reliable AI solutions. Maintain technical documentation, automated tests, reusable components, version control, and engineering best practices throughout the AI application lifecycle. Requirements 6–12 years of overall experience in software engineering, AI/ML engineering, data engineering, or related technical domains, with hands-on experience developing AI-powered applications. Strong programming skills in Python, including application development, API integration, data processing, debugging, testing, and exception handling. Hands-on experience building and deploying Generative AI applications using LLM APIs or open-source language models. Strong understanding of RAG architecture, document ingestion, text preprocessing, chunking strategies, embeddings, vector databases, retrieval optimization, and grounded response generation. Practical experience with LLM orchestration frameworks such as LangChain, LangGraph, or LlamaIndex. Experience with vector databases and search technologies such as Azure AI Search, Pinecone, Qdrant, Weaviate, Chroma, FAISS, Elasticsearch, or OpenSearch. Hands-on experience with prompt engineering, structured output generation, function calling, context management, and LLM integration. Experience processing structured and unstructured documents, including PDFs, Excel files, Word documents, scanned documents, and complex tables, using document parsers, OCR, and document intelligence technologies. Knowledge of table extraction, schema normalization, metadata management, data quality validation, and document versioning. Practical experience with LangSmith, MLflow, or equivalent platforms for LLM tracing, experiment tracking, evaluation, observability, and performance optimization. Strong understanding of LLM evaluation methodologies, including retrieval precision and recall, answer correctness, faithfulness, contextual relevance, citation validation, and regression testing. Experience implementing hallucination mitigation, evidence validation, confidence thresholds, fallback mechanisms, and safe abstention strategies. Understanding of LLM and embedding model selection based on accuracy, latency, cost, context length, multilingual capabilities, privacy, and deployment constraints. Experience integrating AI applications with REST APIs, SQL/NoSQL databases, enterprise systems, and external tools. Knowledge of Agentic AI concepts, tool calling, workflow orchestration, state management, and multi-step LLM execution. Familiarity with cloud AI platforms such as Azure OpenAI, Azure AI Foundry, Amazon Bedrock, or Google Vertex AI. Experience with Git, Docker, CI/CD, automated testing, application logging, monitoring, and production deployment practices. Understanding of AI security, access control, data privacy, prompt injection risks, sensitive-data protection, and responsible AI principles. Strong analytical, problem-solving, debugging, communication, and collaboration skills, with the ability to deliver production-ready AI solutions.