Gen AI Engineer (SJ-IQ)

SE Mentor Solutions; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

SE Mentor Solutions in Bengaluru, India seeks a senior AI/full-stack engineer to design and deliver production-grade AI apps. You will develop end-to-end AI solutions using LLMs, RAG, agentic AI frameworks, and multimodal models across text, audio, image, and video data, on Azure cloud services.

You will build scalable AI workloads with Python, TypeScript, REST APIs, microservices, and Azure OpenAI, while optimizing conversational AI, DAX, and automation workflows.

Qualifications

• 6+ years of experience building production-grade full-stack apps.
• Experience delivering AI products and cloud-native services.
• Strong knowledge of LLMs, RAG, and agentic AI frameworks.
• Experience with Azure OpenAI, vector databases, and semantic search.
• Proficient in Python and TypeScript for backend/frontend.
• Familiarity with CI/CD, testing, security, and governance for AI apps.

Responsibilities

• Design and develop end-to-end AI solutions with LLMs and multimodal models.
• Build scalable AI applications using Python, TypeScript, REST APIs and microservices.
• Architect AI agents, DAX, and automation workflows on Azure.
• Implement vector databases and semantic retrieval for knowledge grounding.
• Operate LLMOps/MLOps pipelines, model deployment, evaluation, and monitoring.
• Integrate speech, audio, image, and video generation into AI UX.
• Lead adoption of AI-assisted development and autonomous research workflows.

Skills

Full-stack development

AI product design

LLMs & RAG

MLOps

Python

TypeScript

REST APIs

Microservices

Cloud services

Azure OpenAI

Azure cloud

GitHub Copilot

Distributed systems

Tools

Azure OpenAI

Databricks

AKS

Azure DevOps

Terraform

LLMOps

Job description

6+ years of experience building and delivering production-grade full-stack applications, AI products, and cloud-native services.

Design and develop end-to-end AI solutions using LLMs, RAG, agentic AI frameworks, and multimodal foundation models for text, audio, image, and video generation.

Build scalable AI applications using Python, TypeScript, REST APIs, microservices, and Azure cloud services.

Architect and optimize conversational AI, Digital AI Agents (DAX), GitHub + copilots, and task automation workflows leveraging Azure OpenAI and modern AI platforms.

Implement Vector Database and semantic retrieval solutions to power enterprise knowledge search, reasoning, and grounding capabilities.

Develop and operationalize LLMOps/MLOps pipelines including model deployment, evaluation, observability, prompt management, guardrails, and continuous monitoring.

Integrate speech-to-text, text-to-speech, audio intelligence, image generation, and video generation capabilities into AI-powered user experiences8 using LLM Models & API calls (Gemini, GPT 5 and higher, DALL-E-3.0) .

Build and deploy scalable workloads on Azure, Databricks, AKS/Kubernetes, Azure Data Lake Gen2, and event-driven architectures.

Establish CI/CD, automated testing, security, and governance standards for AI applications using GitHub and Azure DevOps.

Drive adoption of AI-assisted development, coding agents, and autonomous research systems across teams.

Key Technologies

Azure OpenAI

• GPT-4o / DAX Models
• RAG
• Agentic AI
• Vector DBs
• Databricks
• Python
• AKS
• Azure AI Speech
• Image/Video/Audio Generation APIs
• GitHub Copilot
• Azure DevOps
• LLMOps