AI Specialist

Epergne Solutions; Singapore; On-site; SGD 24,000 - 35,000; Full time

Job summary

Epergne Solutions seeks an AI Specialist to design, develop, and deploy LLM-powered systems with agentic workflows. You will work across multi-agent frameworks, optimize prompts and Cost-efficient LLM workflows, and build scalable APIs using FastAPI to serve AI solutions.

You will implement inter-agent communication, integrate MCP and A2A standards, and continuously improve model performance through feedback loops. Immediate joining within two weeks is preferred.

Qualifications

• 5 years of experience in software engineering or applied AI.
• Hands-on experience building production-grade LLM and agentic systems.
• Strong understanding of cloud-based AI platforms.
• Experience deploying AI solutions in enterprise environments.
• Excellent problem-solving and communication skills.
• Immediate joiners within 2 weeks preferred.

Responsibilities

• Design, develop, and deploy LLM-powered and agentic AI systems using multi-agent frameworks.
• Build and optimize prompt strategies, API usage, and cost-efficient LLM workflows.
• Develop scalable and secure backend APIs using FastAPI to serve AI solutions.
• Implement multi-agent architectures with inter-agent communication and task orchestration.
• Integrate agentic workflows into existing applications and business processes.
• Apply MCP and A2A communication standards.
• Build systems with feedback loops to continuously improve model performance and outcomes.

Skills

LLMs

Prompt engineering

Multi-agent frameworks

Python advanced

FastAPI

RESTful API design

Cloud AI platforms

CI/CD for AI

Databricks

Agentic orchestration

Tools

LangChain

LangGraph

CrewAI

Azure AI Studio

AWS Bedrock

Databricks

Job description

Job Role

- AI Specialist

Job Location

Pune/Hyderabad/Chennai/Mysore/Bhubaneswar/Mangalore/Trivandrum/Chandigarh/Jaipur/Nagpur/Indore/Gurgaon/Noida/Bengaluru/Mohali/Coimbatore/Vijayawada/Madurai/Kochi

Experience

5 Years

Roles & Responsibilities

• Design, develop, and deploy LLM-powered and agentic AI systems using multi-agent frameworks
• Build and optimize prompt strategies, API usage, and cost-efficient LLM workflows
• Develop scalable and secure backend APIs using FastAPI to serve AI solutions
• Implement multi-agent architectures with inter-agent communication and task orchestration
• Integrate agentic workflows into existing applications and business processes
• Apply emerging standards such as MCP (Model Context Protocol) and Agent-to-Agent (A2A) communication
• Build systems with feedback loops to continuously improve model performance and outcomes

Skills

• Foundation LLMs (GPT-4, Claude 3.5, Llama 3) and API optimization
• Prompt engineering and cost/performance tuning
• Multi-agent frameworks (LangChain, LangGraph, CrewAI)
• Python (advanced) and FastAPI
• RESTful API design and backend architecture
• Azure AI Studio or AWS Bedrock
• CI/CD for AI workflows
• Databricks (Unity Catalog, Mosaic AI)
• Agentic system design and orchestration

Requirements

• 5 years of experience in software engineering / applied AI
• Hands-on experience building production-grade LLM and agentic systems
• Strong understanding of cloud-based AI platforms
• Experience deploying AI solutions in enterprise environments
• Excellent problem-solving and communication skills
• Immediate joiners to Maximum 2 week Notice period candidates preferred.