Gen AI Developer

Info Way Solutions; Bengaluru; On-site; INR 300,000 - 600,000; Full time

Job summary

Info Way Solutions seeks an experienced GenAI Developer to design, build and deploy GenAI/LLM applications in production. You will craft RAG pipelines, embeddings and vector search, integrating LLMs with enterprise data and APIs.

The role requires hands-on work with OpenAI/Azure OpenAI/AWS Bedrock/Vertex AI, LangChain, vector databases and Python-based services in a cloud environment. Collaboration with AI architects and data teams is essential.

Qualifications

• 5+ years of overall IT/software development experience.
• Strong hands-on experience with Generative AI / LLM.
• Experience with RAG, Prompt Engineering and LLM applications.
• Hands-on experience with OpenAI / Azure OpenAI / AWS Bedrock / Google Vertex AI.
• Experience with LangChain, LangGraph, LlamaIndex or similar frameworks.
• Experience with vector databases such as Pinecone, FAISS, Milvus, Weaviate or PGVector.
• Good understanding of Machine Learning and NLP concepts.
• Experience with REST APIs, microservices and cloud platforms.
• Knowledge of Docker/Kubernetes and CI/CD is preferred.

Responsibilities

• Design, develop and deploy GenAI/LLM applications.
• Build and optimize RAG pipelines, embeddings and vector search solutions.
• Develop AI-powered applications, copilots, chatbots and intelligent agents.
• Integrate LLMs with enterprise applications, APIs and data sources.
• Implement prompt engineering, model evaluation and optimization.
• Develop scalable AI services using Python.
• Work with cloud AI services and deploy solutions into production.
• Collaborate with AI Architects, Data Engineers and application teams.

Skills

GenAI/LLM

RAG pipelines

Prompt engineering

LangChain

Vector databases

REST APIs

Docker/Kubernetes

Python

Cloud platforms

NLP concepts

Tools

OpenAI

Azure OpenAI

AWS Bedrock

Google Vertex AI

Pinecone

FAISS

Milvus

Weaviate

PGVector

Job description

We are looking for a skilled GenAI Developer / AI Engineer with 5+ years of experience in software development and hands-on experience building Generative AI, LLM and RAG-based solutions.

Key Responsibilities

• Design, develop and deploy GenAI/LLM applications.
• Build and optimize RAG pipelines, embeddings and vector search solutions.
• Develop AI-powered applications, copilots, chatbots and intelligent agents.
• Integrate LLMs with enterprise applications, APIs and data sources.
• Implement prompt engineering, model evaluation and optimization.
• Develop scalable AI services using Python.
• Work with cloud AI services and deploy solutions into production.
• Collaborate with AI Architects, Data Engineers and application teams.

Must-Have Skills

• 5+ years of overall IT/software development experience.
• Strong hands-on experience with Generative AI / LLM.
• Experience with RAG, Prompt Engineering and LLM applications.
• Hands-on experience with OpenAI / Azure OpenAI / AWS Bedrock / Google Vertex AI.
• Experience with LangChain, LangGraph, LlamaIndex or similar frameworks.
• Experience with vector databases such as Pinecone, FAISS, Milvus, Weaviate or PGVector.
• Good understanding of Machine Learning and NLP concepts.
• Experience with REST APIs, microservices and cloud platforms.
• Knowledge of Docker/Kubernetes and CI/CD is preferred.

Good to Have

• Experience with Agentic AI / Multi-Agent systems.
• Experience with LLM fine-tuning or model customization.
• Knowledge of MLOps/LLMOps.

Ideal Profile

A hands-on AI/GenAI Engineer who has built and deployed real-world LLM/RAG applications in production.