AI Fullstack Developer

Overview

Build and scale generative AI applications, handling full‑stack development and prompt engineering.

Key Responsibilities

• llm evaluation
• prompt engineering
• ai engineering
• model validation
• stakeholder mgmt
• team leadership

Tasks

-Stakeholder Communication: Translate complex needs into clear terms for technical and non-technical stakeholders, ensuring alignment on project goals and expected outcomes. -Understand Business Needs: Cultivate a growth mindset, build an understanding of RealPage’s business processes, products, and challenges to better align AI solutions with organizational goals. -Agentic AI Engineering: Evaluate and utilize appropriate language models from different vendors (e.g., OpenAI GPT, Google Gemini, xAI Grok, Anthropic Claude) to develop AI applications such as text generation, summarization, conversational assistants, OCR, generative analytics and copilots, agents, and beyond. Assess and utilize appropriate AI tools, LLMs, vector databases, RAG (Retrieval-Augmented Generation) solutions, and Agentic frameworks based on project needs. -Leadership and Mentorship: Provide technical leadership and mentorship to ML engineers and Data Scientists fostering a collaborative team environment and improving overall team effectiveness. -Stay Current in AI Advancements: Track the latest AI research, tools, and trends, and adopt innovative approaches to continuously enhance project outcomes and drive improvement. Not being shy about doing PoCs and prototypes. -Establish Evaluation Frameworks: Develop and maintain frameworks to validate and measure LLM performance, testing models across a range of capabilities and edge cases for optimal outcomes. -Cross-Functional Collaboration: Work with interdisciplinary teams, including AI engineers, software engineers, product managers, and domain experts, to create integrated Agentic AI experiences. -Master Prompt Engineering: Design effective prompts to minimize hallucinations, anticipate and resolve edge cases, and ensure the robustness of generative AI solutions.

Requirements

• generative ai
• llm
• react
• docker
• kubernetes
• prompt engineering

What You Bring

-9+ years in Software Engineering and/or Data Science, with at least 2 years in Generative AI and large language models (LLMs). -Demonstrated ability to lead projects and mentor team members in Agile environments, driving collaboration and fostering team effectiveness. -Speech-to-Text (STT) APIs -Familiarity with Vector embeddings, RAG architectures and Agentic frameworks for sophisticated generative AI applications. -Tailor Full User Experience: Capable of writing code for UIs (React / Vue / Svelte etc) and integrations (MCP, webRTC, REST, gRCP). -Exceptional communication skills to effectively convey complex technical subjects to both technical and non-technical stakeholders. -Text-to-Speech (TTS) engines -Familiarity with observability tools for AI systems (e.g., LangSmith, OpenTelemetry). -Degree in Computer Science, Machine Learning, Data Science, or a related field, or equivalent industry experience. -Understanding of dialogue management and multi-turn conversation design in voice interfaces. -Expertise with cloud platforms for AI (AWS, GCP, Azure) and experience with containerization (Docker), orchestration (Kubernetes), and CI/CD practices. -Experience with agentic AI frameworks (e.g., OpenAI Agent SDK, AI SDK, LangChain, AutoGen, CrewAI, Mastra). -Proficiency in prompt engineering to enhance model output reliability and quality. -Real-time audio streaming and integration with WebRTC, Twilio Voice, or Socket.IO -Strong proficiency with modern Python, JavaScript/TypeScript and SQL, experience in writing production-grade code. -Experience building voice-enabled AI agents or voice chatbots using:

People Also Searched For

About realpage india

Nope

Sector Specialisms