AI Developer

UST; Hyderabad; On-site; INR 2,200,000 - 3,200,000; Full time

Job summary

UST in Hyderabad seeks a seasoned AI/ML professional with 6+ years of experience in development, software engineering or testing. You will work with Copilot, Claude, OpenAI and other LLM platforms to build enterprise-grade AI solutions and shape multi-model AI ecosystems.

You will design, deploy and monitor AI systems with robust governance, AI guardrails, RAG pipelines, MCP servers, and token/ cost optimization, while collaborating across teams to deliver scalable AI experiences in production.

Qualifications

• 6+ years of professional experience in AI/ML development, software engineering, or testing.
• Hands-on experience with Copilot, Claude, OpenAI, or other LLM-based platforms.
• Dedicated testing and QA experience within AI/ML systems.
• Proven experience delivering production-grade AI applications.
• Experience working with multi-model AI ecosystems across OpenAI, Anthropic, Microsoft, Google, Meta, and similar platforms.

Responsibilities

• Build and maintain enterprise-grade AI tools leveraging LLMs, Copilots, and AI agent frameworks.
• Implement AI Guardrails to ensure application safety, compliance, responsible AI usage, and security.
• Design and optimize Context Compression strategies to reduce token consumption, improve performance, and control operational costs.
• Develop and integrate RAG pipelines and MCP Server-based solutions to enable contextual and scalable AI experiences.
• Deploy, monitor, and maintain productionized AI solutions with appropriate observability, governance, and feedback mechanisms.

Skills

AI/ML development

Software engineering

Testing

Production-grade AI

Multi-model AI ecosystems

Tools

LangChain

LlamaIndex

OpenAI APIs

Anthropic APIs

Azure OpenAI

Microsoft Copilot

Prompt Engineering

RAG

MCP Servers

AI Guardrails

Context Compression

Job description

• 6+ years of professional experience in AI/ML development, software engineering, or testing.
• Hands-on experience with Copilot, Claude, OpenAI, or other LLM-based platforms.
• Dedicated testing and QA experience within AI/ML systems.
• Experience working with multi-model AI ecosystems across OpenAI, Anthropic, Microsoft, Google, Meta, and similar platforms.
• Hands-on experience in designing, developing, and deploying AI-powered tools and applications in enterprise environments.
• Demonstrated experience implementing and managing productionized AI solutions, including monitoring, governance, scalability, and performance optimization.
• Experience implementing RAG (Retrieval Augmented Generation) solutions and integrating with vector databases.
• Exposure to MCP (Model Context Protocol) servers and AI agent frameworks.
• LangChain
• OpenAI APIs
• Anthropic APIs
• Prompt Engineering
• RAG (Retrieval Augmented Generation)
• AI Guardrails implementation and validation
• Context Compression and Token Optimization techniques

Role Description

• 6+ years of professional experience in AI/ML development, software engineering, or testing.
• Hands-on experience with Copilot, Claude, OpenAI, or other LLM-based platforms.
• Dedicated testing and QA experience within AI/ML systems.
• Proven experience delivering production-grade AI applications.
• Experience working with multi-model AI ecosystems across OpenAI, Anthropic, Microsoft, Google, Meta, and similar platforms.
• Hands-on experience in designing, developing, and deploying AI-powered tools and applications in enterprise environments.
• Demonstrated experience implementing and managing productionized AI solutions, including monitoring, governance, scalability, and performance optimization.
• Experience implementing RAG (Retrieval Augmented Generation) solutions and integrating with vector databases.
• Exposure to MCP (Model Context Protocol) servers and AI agent frameworks.

AI & Machine Learning Technologies

• LangChain
• LlamaIndex
• OpenAI APIs
• Anthropic APIs
• Azure OpenAI
• Microsoft Copilot
• Prompt Engineering
• RAG (Retrieval Augmented Generation)
• MCP (Model Context Protocol) Servers
• AI Guardrails implementation and validation
• Context Compression and Token Optimization techniques

Key Responsibilities

AI Development & Implementation

• Build and maintain enterprise-grade AI tools leveraging LLMs, Copilots, and AI agent frameworks.
• Implement AI Guardrails to ensure application safety, compliance, responsible AI usage, and security.
• Design and optimize Context Compression strategies to reduce token consumption, improve performance, and control operational costs.
• Develop and integrate RAG pipelines and MCP Server-based solutions to enable contextual and scalable AI experiences.
• Deploy, monitor, and maintain productionized AI solutions with appropriate observability, governance, and feedback mechanisms.

The Candidate Should Possess a Strong Understanding Of

• Large Language Models (LLMs)
• Generative AI solution architecture
• Retrieval Augmented Generation (RAG)
• Vector Databases
• NLP/NLU concepts
• AI Ethics and Responsible AI
• Bias Detection and Mitigation
• AI Security and Data Privacy
• Regulatory Compliance Requirements
• AI Guardrails, content filtering, prompt injection prevention, and responsible AI controls
• Context Compression, token management, and cost optimization strategies
• MCP (Model Context Protocol) architecture and AI agent integrations
• Best practices for production deployment, monitoring, and governance of AI solutions

Required Technical Competencies

AI & LLM Expertise

• Microsoft Copilot Suite
• GitHub Copilot
• Claude (Opus, Sonnet, Haiku)
• OpenAI GPT Models
• Prompt Engineering
• Few-shot Learning Techniques
• Model Selection & Evaluation
• Hands-on experience building AI tools and enterprise AI applications
• Design and implementation of AI Guardrails
• Context Compression and Token Optimization techniques
• RAG architecture design and implementation
• MCP Server integration and configuration
• Production deployment and lifecycle management of AI solutions
• Experience implementing AI Guardrails and Responsible AI frameworks in enterprise environments.
• Hands-on experience optimizing LLM applications for token efficiency, latency, and cost management.
• Experience working with MCP servers, AI agents, and multi-agent architectures.
• Experience deploying and supporting productionized AI solutions at scale.
• Experience building custom AI copilots, assistants, and enterprise AI tools.

Skills

• LangChain, LLMs, MLOps, Python, LlamaIndex, OpenAI, NoSQL, NLP, SQL, Prompt Engineering, Machine Learning, AI development, Guardrails, RAG