Polestar Analytics - AI Engineer - Generative AI & Agentic Systems

Polestar Analytics; Kolkata District; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Polestar Analytics invites an AI Engineer specializing in Generative AI and Agentic Systems to join our enterprise AI initiatives in Kolkata. You will design, build, and deploy LLM-powered solutions, with emphasis on RAG, multi-agent orchestration, and scalable platforms.

We seek 3–8 years of hands-on experience, strong Python and API skills, and a track record of delivering production-grade AI services within enterprise environments.

Qualifications

• 3–8 years of hands-on experience designing, developing, and deploying enterprise-grade AI solutions.

Responsibilities

• Design, develop, and deploy enterprise-grade applications powered by LLMs and foundation models.
• Build RAG solutions leveraging vector databases and enterprise knowledge repositories.
• Develop conversational AI assistants, enterprise copilots, and workflow automation.
• Implement advanced prompt engineering techniques including CoT, ReAct, and Multi‑Step Reasoning.
• Design multi-agent AI systems with autonomous planning, reasoning, and execution.
• Build agent orchestration frameworks integrating enterprise apps and external services.
• Implement agent memory management, communication protocols, and human-in-the-loop workflows.
• Develop scalable AI services, APIs, and reusable platform components.
• Integrate AI with enterprise platforms like CRM, ERP, and Data Warehouses.
• Design AI governance, monitoring, and evaluation frameworks.
• Evaluate AI applications for relevance, safety, and performance.
• Build automated evaluation pipelines and testing frameworks.
• Optimize inference performance, latency, and costs.
• Collaborate with Product, Engineering, Data Science, and Business teams.
• Stay updated with generative AI trends.

Skills

Generative AI

Agentic AI

RAG

Multi-agent systems

Prompt engineering

API design

Education

Bachelor's or Master's in CS/AI/DS

Tools

OpenAI

Claude

Gemini

Llama

Mistral

Qwen

LangGraph

LangChain

CrewAI

AutoGen

Semantic Kernel

Pydantic AI

Vector Databases

Knowledge Graphs

GraphRAG

Python

FastAPI

REST APIs

Docker

Kubernetes

GitHub Actions

CI/CD

Azure AI Foundry

Azure OpenAI

Vertex AI

AWS Bedrock

Databricks AI

Job description

Position Summary

We are looking for a highly skilled AI Engineer - Generative AI & Agentic Systems with 3 - 8 years of experience in designing, developing, and deploying enterprise-grade AI solutions powered by Large Language Models (LLMs).

The ideal candidate will have hands‑on expertise in Generative AI, Agentic AI, Retrieval‑Augmented Generation (RAG), multi‑agent architectures, and AI orchestration frameworks.

This role involves building intelligent AI assistants, enterprise copilots, autonomous workflows, and scalable AI platforms that drive business innovation and operational efficiency.

Strategic Responsibilities

• Design, develop, and deploy enterprise‑grade applications powered by Large Language Models (LLMs) and foundation models.
• Build Retrieval‑Augmented Generation (RAG) solutions leveraging vector databases, enterprise knowledge repositories, and GraphRAG architectures.
• Develop conversational AI assistants, enterprise copilots, intelligent chatbots, and workflow automation solutions.
• Implement advanced prompt engineering techniques including Chain of Thought (CoT), ReAct, Self‑Reflection, Multi‑Step Reasoning, and Tool Calling.
• Design and develop multi‑agent AI systems capable of autonomous planning, reasoning, task decomposition, and execution.
• Build agent orchestration frameworks integrating enterprise applications, APIs, and external services.
• Implement agent memory management, communication protocols, and human‑in‑the‑loop workflows.
• Develop scalable AI services, APIs, and reusable AI platform components for enterprise deployments.
• Integrate AI solutions with enterprise platforms including CRM, ERP, Supply Chain, Data Warehouses, and Knowledge Management systems.
• Design and implement AI governance, monitoring, observability, and evaluation frameworks.
• Evaluate AI applications for relevance, groundedness, hallucination, safety, accuracy, and overall performance.
• Build automated evaluation pipelines, testing frameworks, and continuous model validation processes.
• Optimize inference performance, latency, scalability, token utilization, and infrastructure costs.
• Collaborate with Product, Engineering, Data Science, and Business teams to deliver production‑ready AI solutions.
• Stay updated with emerging trends in Generative AI, Agentic AI, LLMs, and enterprise AI platforms.

Technical Skills

• Generative AI : OpenAI, Claude, Gemini, Llama, Mistral, Qwen.
• Agentic AI Frameworks : LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, Pydantic AI.
• RAG & Knowledge Systems : Vector Databases, Knowledge Graphs, GraphRAG.
• Programming : Python, FastAPI, REST APIs, Async Programming.
• Cloud & AI Platforms : Azure AI Foundry, Azure OpenAI, Vertex AI, AWS Bedrock, Databricks AI.
• DevOps & Deployment : Docker, Kubernetes, GitHub Actions, CI/CD.

Educational Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field.

(ref:hirist.tech)