Artificial Intelligence Engineer

Coforge; Bengaluru; On-site; INR 1,200,000 - 2,800,000; Full time

Job summary

Coforge in Bengaluru, India is seeking an experienced AI Engineer to design, deploy, and optimize AI/Gen AI solutions in production. The role involves hands‑on development with LLMs, RAG pipelines, agentic frameworks (LangChain, LangGraph, AutoGen), and integration with enterprise systems.

The candidate will work closely with architects and product teams to deliver scalable, reliable, and efficient AI applications.

Qualifications

• 5+ years in software engineering / AI / ML roles.
• 2+ years hands-on experience with AI/ML or Gen AI applications.

Responsibilities

• Build and deploy LLM-based applications including chatbots, copilots, and automation tools.
• Develop agent-based solutions using LangChain, LangGraph, AutoGen.
• Experience with MCP for secure tool access and scalable integration in agentic AI systems.
• Implement prompt engineering, prompt tuning, context handling, tool-calling, memory and orchestration.
• Integrate agents with enterprise systems via APIs and databases.

Skills

LLMs

LangChain

LangGraph

AutoGen

RAG pipelines

MCP

Docker

Kubernetes

CI/CD

Responsible AI

Tools

Pinecone

FAISS

Azure AI

AWS AI

Job description

Notice Period: Immediate to 20 days ONLY

We are looking for a skilled AI Engineer to build, deploy, and optimize AI/Gen AI solutions in production. The role involves hands‑on development with LLMs, RAG pipelines, Agentic frameworks (LangChain, LangGraph, AutoGen), and integration with enterprise systems. The candidate will work closely with architects and product teams to deliver scalable, reliable, and efficient AI applications.

Key Responsibilities:

• Build and deploy LLM‑based applications including chatbots, copilots, and automation tools
• Develop agent-based solutions using LangChain, LangGraph, AutoGen
• Experience working with Model Context Protocol (MCP) and MCP Gateway for managing secure tool access, authentication, and scalable integration in agentic AI systems.
• Implement prompt engineering, prompt tuning, context handling, tool‑calling, memory, and workflow orchestration
• Integrate agents with enterprise systems via APIs
• Work with Vector Databases such as Pinecone, FAISS, Azure AI Search
• Implement embedding pipelines, indexing, and semantic search
• Optimize relevance, latency, and retrieval accuracy
• Build and integrate REST APIs for AI services
• Connect AI systems with databases, SaaS platforms, and internal enterprise systems
• Enable real‑time and batch AI processing workflows
• Deploy AI solutions using Docker, Kubernetes, CI/CD pipelines
• Work on model lifecycle management, versioning, and monitoring
• Monitor logs, traces, token usage, and system performance
• Continuously improve model responses and system reliability

Core Experience

• 5+ years in software engineering / AI / ML roles
• 2+ years hands‑on experience with AI/ML or Gen AI applications

Technical Skills

• Experience with LLMs (GPT, Claude, LLaMA, Mistral or similar)
• Hands‑on with LangChain / LangGraph / AutoGen
• Experience building RAG systems
• Experience in using MCP
• Familiarity with Vector Databases (Pinecone, FAISS, etc.)
• Knowledge of Azure / AWS AI services
• Exposure to Docker, Kubernetes, CI/CD pipelines
• Knowledge of LLM guardrails and responsible AI practices