Solutions Architect

WebMD LLC; Navi Mumbai; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

A leading healthcare technology organization is seeking a Full-Stack GenAI Architect to lead AI integration within their software products. You will serve as a hands-on engineer and mentor, guiding R&D initiatives and driving AI strategy. Applicants should have 10+ years in software engineering and 1+ years with frontier LLMs, along with strong skills in Python and TypeScript. This role offers a unique chance to shape AI's impact on real-world software solutions.

Qualifications

• 10+ years in software engineering with deep technical fluency.
• 1+ years hands-on experience with frontier LLMs.
• Strong proficiency in Python, TypeScript, or similar.

Responsibilities

• Evaluate emerging AI models and tools for innovation.
• Design scalable AI integrations within software.
• Mentor engineers on AI utilization best practices.

Skills

Software engineering

AI technologies

Team leadership

Python

TypeScript

Prompt engineering

Tools

Google ADK

LangGraph

Langfuse

Job description

Overview

We are looking for a Full-Stack GenAI Architect to lead the exploration and integration of Large Language Models (LLMs) and modern AI techniques across our software products. You’ll serve as both a hands-on engineer and thought leader, helping define our AI strategy, drive R&D initiatives, and accelerate the adoption of AI across product lines.

This is a unique opportunity to shape how AI transforms real-world software — from developer workflows and automation to end-user product experiences.

Roles and Responsibilities

• Research & Experimentation: Continuously evaluate emerging AI models (OpenAI GPT, Anthropic Claude, Google Gemini, Qwen, GLM), agent frameworks (Google ADK, LangGraph), and tools (Vector DBs, Agent Observability, Prompt Optimization, Agent Evaluations, Agent Memory) to identify practical opportunities for innovation.
• Architecture & Implementation: Design and implement scalable Agentic AI integrations within existing business processes and software, ensuring reliability, performance, and data privacy.
• Prototyping & R&D: Build proof-of-concepts and pilot features to validate new approaches — from prompt engineering and fine-tuning to multi-agent orchestration.
• Technical Leadership: Mentor engineers across the organization on AI utilization best practices, lead architecture reviews, and contribute to shared internal libraries and model-integration frameworks.
• Industry Awareness & Advocacy: Track and evaluate industry trends, tools, and research; represent the company’s AI engineering direction through internal knowledge-sharing and occasional external engagement.

Requirements

• 10+ years in software engineering with deep technical fluency in the development, design and architecture of modern full-stack web applications. Strong foundation to support the full stack, including front-end, back-end, databases (relational and NoSQL), API design, microservices, caching, performance tuning, security best practices, and common software design patterns.
• 1+ years hands-on experience working with frontier LLMs and building AI agents.
• Demonstrated technical leadership and mentorship across an engineering department, with strong strategic thinking and problem-solving.
• Strong proficiency in Python, TypeScript, or similar, with experience integrating model APIs and building AI-enabled features.
• Working knowledge of AI Agent architecture, AI Agent patterns, prompt engineering, context engineering and RAG.
• Familiarity with AI-enhanced developer workflows and Agentic AI IDEs (e.g. Cursor, Cline, Replit), for code generation, documentation assistants, or autonomous agents.
• A passion for continuous learning, experimentation, and bringing emerging AI concepts into production environments.
• Excellent communication skills and the ability to influence cross-functional teams through clear technical reasoning and vision.

Bonus

• Experience with Google ADK, Langgraph and Langfuse (or similar technologies).
• Integration with open source models, and fine tuning of those open source models.
• Production deployment of multi-agent orchestration.

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status.