GenAI Enginner

Platly Infotech; Hyderabad, Chennai District, Bengaluru; On-site; INR 1,500,000 - 3,000,000; Full time

Job summary

Platly Infotech seeks a software engineer to design, develop, and deploy Generative AI and LLM-based applications for real-world business use cases in Hyderabad. You will build RAG pipelines, develop GenAI solutions with Python, LangChain, and LlamaIndex, and integrate OpenAI/Azure OpenAI/Gemini models.

Responsibilities include prompt engineering, embeddings, semantic search, vector databases, and document-processing workflows; building REST APIs with FastAPI or Flask; and deploying GenAI apps

Qualifications

• 3–10 years of software development, AI/ML, or Generative AI experience.
• Strong hands-on experience with Python and Generative AI/LLMs.
• Experience with RAG, Prompt Engineering, LangChain/LlamaIndex, Vector Databases, and LLM APIs.
• Experience with OpenAI/Azure OpenAI/AWS Bedrock/Gemini is preferred.
• Strong understanding of NLP, embeddings, semantic search, and AI application development.
• Experience with FastAPI/REST APIs and cloud platforms is an advantage.
• Exposure to AI Agents, LLM evaluation, fine-tuning, or LLMOps is a plus.
• Strong problem-solving and communication skills.
• Candidates with production-grade GenAI solutions will be preferred.

Responsibilities

• Design, develop, and deploy Generative AI and LLM-based applications for real-world business use cases.
• Build and optimize RAG pipelines using enterprise and unstructured data.
• Develop GenAI solutions using Python, LangChain, LlamaIndex, or similar frameworks.
• Integrate and work with LLMs such as OpenAI, Azure OpenAI, AWS Bedrock, Gemini, or equivalent models.
• Implement prompt engineering, embeddings, semantic search, and vector database solutions.
• Develop document-processing workflows including data ingestion, chunking, retrieval, and knowledge extraction.
• Build REST APIs and AI services using FastAPI, Flask, or similar technologies.
• Develop AI Agents / Agentic AI workflows to automate complex business processes.
• Evaluate and improve LLM applications for accuracy, relevance, hallucination, latency, and cost.
• Collaborate with software engineers, data scientists, architects, and business teams to deliver scalable AI solutions.
• Deploy and maintain GenAI applications on AWS, Azure, or GCP environments.
• Participate in solution design, code reviews, testing, troubleshooting, and production support.

Skills

Python

Generative AI/LLMs

LangChain

LlamaIndex

REST APIs

Prompt engineering

Embeddings

Semantic search

Vector databases

Cloud platforms

Tools

FastAPI

Flask

OpenAI APIs

Azure OpenAI

AWS Bedrock

Gemini

Job description

Roles & Responsibilities

• Design, develop, and deploy Generative AI and LLM-based applications for real-world business use cases.
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines using enterprise and unstructured data.
• Develop GenAI solutions using Python, LangChain, LlamaIndex, or similar frameworks.
• Integrate and work with LLMs such as OpenAI, Azure OpenAI, AWS Bedrock, Gemini, or equivalent models.
• Implement prompt engineering, embeddings, semantic search, and vector database solutions.
• Develop document-processing workflows including data ingestion, chunking, retrieval, and knowledge extraction.
• Build REST APIs and AI services using FastAPI, Flask, or similar technologies.
• Develop AI Agents / Agentic AI workflows to automate complex business processes.
• Evaluate and improve LLM applications for accuracy, relevance, hallucination, latency, and cost.
• Collaborate with software engineers, data scientists, architects, and business teams to deliver scalable AI solutions.
• Deploy and maintain GenAI applications on AWS, Azure, or GCP environments.
• Participate in solution design, code reviews, testing, troubleshooting, and production support.

Preferred Candidate Profile

• 3 - 10 years of experience in software development, AI/ML, or Generative AI.
• Strong hands-on experience with Python and Generative AI/LLMs.
• Good experience in RAG, Prompt Engineering, LangChain/LlamaIndex, Vector Databases, and LLM APIs.
• Experience with OpenAI/Azure OpenAI/AWS Bedrock/Gemini is preferred.
• Strong understanding of NLP, embeddings, semantic search, and AI application development.
• Experience with FastAPI/REST APIs and cloud platforms is an advantage.
• Exposure to AI Agents, LLM evaluation, fine-tuning, or LLMOps is a plus.
• Strong problem-solving and communication skills.
• Candidates with experience delivering production-grade GenAI solutions will be preferred.