AI Engineer

Easyrewardz Software Services; Gurugram District; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Easyrewardz Software Services in Gurugram invites an experienced AI Engineer to design and scale GenAI-powered products. You will build and optimize RAG pipelines, deploy LLM-based apps, and create reliable agentic AI workflows for production use.

You will work across Product, Data Engineering, and Analytics to translate business needs into scalable AI solutions, implement guardrails for safety, monitor performance, and stay current with the GenAI ecosystem.

Qualifications

• 5 years of total experience in software/data engineering, with 2–3 years AI/GenAI solutions in a similar industry.
• Experience building RAG-based solutions end-to-end (retrieval, indexing, chunking, embeddings, vector search).
• Hands-on experience with LLMs (OpenAI, Anthropic, open-source models) — prompt engineering, fine-tuning, evaluation.
• Practical experience building agentic AI systems — tool use, multi-agent orchestration, task planning/execution loops.
• Proficiency in Python and AI/ML frameworks (e.g., LangChain, LlamaIndex, Hugging Face, or similar).
• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus, or similar).
• Solid understanding of API design and integration for AI-powered applications.
• Familiarity with cloud platforms (AWS/Azure/GCP) for deploying AI workloads.
• Strong understanding of software engineering fundamentals — version control, testing, CI/CD.
• Good problem-solving skills with the ability to work in a fast-paced, cross-functional environment.

Responsibilities

• Design, develop, and deploy RAG pipelines including chunking strategies, embedding generation, vector database integration, and retrieval optimization.
• Build and fine-tune LLM-based applications, including prompt engineering, evaluation, and guardrails for accuracy and safety.
• Architect and implement agentic AI workflows — multi-step reasoning, tool-calling, memory management, and orchestration across agents.
• Integrate LLM/agentic solutions with internal and external APIs, databases, and business systems.
• Optimize model performance, latency, and cost across inference pipelines.
• Collaborate with Product, Data Engineering, and Analytics teams to translate business requirements into scalable AI solutions.
• Implement evaluation frameworks to monitor hallucination rates, retrieval accuracy, and response quality.
• Stay current with the evolving LLM/GenAI ecosystem (new models, frameworks, and techniques) and evaluate their applicability.
• Ensure solutions are production-ready — including logging, monitoring, versioning, and error handling.
• Document architecture, workflows, and technical decisions for internal knowledge sharing.

Skills

RAG pipelines

LLM experience

Agentic AI

Python

Vector databases

API integration

Cloud platforms

CI/CD basics

Problem solving

Tools

LangChain

LlamaIndex

HuggingFace

Job description

About the Role

We are looking for an experienced AI Engineer to join our team and help build and scale GenAI-powered products. The ideal candidate has hands-on experience designing, deploying, and optimizing RAG (Retrieval-Augmented Generation) based solutions, working with LLMs, and building agentic AI systems that operate reliably in production environments.

Key Responsibilities

• Design, develop, and deploy RAG pipelines including chunking strategies, embedding generation, vector database integration, and retrieval optimization.
• Build and fine-tune LLM-based applications, including prompt engineering, evaluation, and guardrails for accuracy and safety.
• Architect and implement agentic AI workflows — multi-step reasoning, tool-calling, memory management, and orchestration across agents.
• Integrate LLM/agentic solutions with internal and external APIs, databases, and business systems.
• Optimize model performance, latency, and cost across inference pipelines.
• Collaborate with Product, Data Engineering, and Analytics teams to translate business requirements into scalable AI solutions.
• Implement evaluation frameworks to monitor hallucination rates, retrieval accuracy, and response quality.
• Stay current with the evolving LLM/GenAI ecosystem (new models, frameworks, and techniques) and evaluate their applicability.
• Ensure solutions are production-ready — including logging, monitoring, versioning, and error handling.
• Document architecture, workflows, and technical decisions for internal knowledge sharing.

Required Skills & Experience

• 5 years of total experience in software/data engineering, with 2–3 years working on AI/ML or GenAI solutions in a similar industry.
• Proven experience building RAG-based solutions end-to-end (retrieval, indexing, chunking, embeddings, vector search).
• Strong hands-on experience working with LLMs (OpenAI, Anthropic, open-source models, etc.) — prompt engineering, fine-tuning, and evaluation.
• Practical experience building agentic AI systems — tool use, multi-agent orchestration, task planning/execution loops.
• Proficiency in Python and common AI/ML frameworks (e.g., LangChain, LlamaIndex, Hugging Face, or similar).
• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus, or similar).
• Solid understanding of API design and integration for AI-powered applications.
• Familiarity with cloud platforms (AWS/Azure/GCP) for deploying AI workloads.
• Strong understanding of software engineering fundamentals — version control, testing, CI/CD.
• Good problem-solving skills with the ability to work in a fast-paced, cross-functional environment.