Jobs in Hyderabad, India (Now Hiring) — 13,200 open at 758 companies — Page 406

Overview

RealPage is at the forefront of the Generative AI revolution, dedicated to shaping the future of artificial intelligence within the Property Tech domain. Our Agentic AI team is focused on driving innovation by building next generation AI applications and enhancing existing systems with Generative AI capabilities. 

We are seeking an AI Engineer to help us with the development, deployment, and scaling of advanced AI applications that address real-world challenges. In this role, you will focus on building and enhancing AI-powered applications within the PropTech domain. You will work under the guidance of senior engineers to implement features using large language models (LLMs), Retrieval-Augmented Generation (RAG), and agentic frameworks. 

You will help prototype, integrate, and test AI capabilities in production workflows—learning how to turn cutting-edge research into reliable products for our users and clients. 

Responsibilities

AI Application Development

• Implement features for AI applications such as: 
• Conversational assistants and copilots 
• Text generation, summarization, and content classification 
• Basic OCR and document understanding workflows 
• Consume and integrate external foundation models (e.g., OpenAI GPT, Claude, Gemini, Llama, Mistral) via APIs. 
• Use and extend internal AI tooling, SDKs, and templates created by senior team members. 

Prompt Engineering & RAG Support

• Design and optimize prompts and system instructions to:  
• Improve task completion, reliability, and latency  
• Minimize hallucinations and toxic/unsafe outputs  
• Implement structured outputs (JSON/JSON Schema)   
• Develop function/tool calling and prompts that help AI call them properly  
• Integrate safety/guardrail layers (e.g., content moderation APIs, Guardrails AI, Rebuff, custom policies) to keep conversations focused  
• Assist with configuring RAG pipelines: 
• Creating embeddings and storing them in vector databases (e.g., Google Vertex AI, PGVector, Pinecone, etc.) 
• Implement knowledge retrieval process that draws from multiple sources and uses reranking to improve the response quality.   
• Help test prompts and retrieval quality to reduce hallucinations and improve relevance. 

Front-End & Integration Work

• Build and maintain front-end components for AI experiences (e.g., in React / Vue / Svelte / Web RTC). 
• Integrate AI APIs into back-end services (e.g., via REST, gRPC, WebSockets, Model Context Protocol (MCP)). 
• Implement streaming responses for chat- or copilot-style interfaces. 

Evaluation, Testing & Observability (Hands-On Execution)

• Write unit, integration, and regression tests for AI features. 
• Run evaluation scripts and log results for model quality metrics (e.g., accuracy, relevance, latency, cost). 
• Work with AI observability tools (e.g., LangSmith, OpenTelemetry, etc.) under guidance. 

Collaboration & Learning

• Collaborate with AI Engineers, Data Scientists, Product Managers, and Designers to deliver features. 
• Participate in code reviews, design sessions, and sprint ceremonies. 
• Stay up-to-date with AI trends and share learnings with the team (e.g., new model APIs, open-source tools, agents, or guardrails). 

Qualifications

• 0–2 years of experience in Software Engineering, Machine Learning, or Data Science (internships or projects acceptable). 
• Bachelor’s degree in Computer Science, Data Science, Engineering, or related field, or equivalent practical experience. 
• Solid programming skills in: 
• Python (for AI pipelines, scripting) 
• JavaScript/TypeScript (for front-end or Node-based services) 
• Working with coding assistants like Windsurf, Cursor, Codex, etc. 
• Basic familiarity with: 
• REST APIs and JSON 
• SQL and one relational database (e.g., PostgreSQL, MySQL) 
• Git and basic CI/CD workflows 
• Exposure to at least one of the following through coursework, projects, or internships: 
• Large language model APIs (OpenAI, Claude, Gemini, etc.) 
• Vector embeddings and vector databases 
• RAG concepts and/or LangChain/LlamaIndex 
• Strong debugging and problem-solving skills; willingness to ask questions and seek feedback. 
• Good verbal and written communication skills. 

 

Nice-to-Have Skills 

• Internship or project experience with: 
• LLM-based chatbots, copilots, or document Q&A 
• Cloud platforms (GCP, Azure, AWS) 
• Containerization (Docker) 
• Familiarity with: 
• Agentic AI frameworks (OpenAI Agents SDK, Google ADK, LangChain or similar) 
• Front-end frameworks (React preferred), TailwindCSS, or design systems 
• Basic AI safety/guardrails tools (e.g., OpenAI Guardrails API including Moderation API, Llama Guard, content filters, PII redaction) 
• Exposure to voice interfaces: 
• Using STT (e.g., Whisper) or TTS (e.g. ElevenLabs) 
• Basic WebRTC, Socket.IO, or Twilio Voice integrations.