GenAI / AI Engineer

Prasanz; Hyderabad; On-site; INR 1,800,000 - 3,400,000; Full time

Job summary

Prasanz in Hyderabad, India, is hiring two Generative AI Engineers to design and deploy production-grade AI features. You will architect retrieval-augmented generation structures, fine-tune models, and build scalable FastAPI endpoints for real-time outputs.

You will collaborate with product squads to identify AI enablement opportunities, optimize model pipelines, and minimize token costs while ensuring robust performance.

Qualifications

• 4+ years of software engineering experience with 2+ years in AI/ML model integrations.
• Proficient in Python and libraries such as LangChain, LlamaIndex, PyTorch, and Hugging Face.
• Experience configuring and querying production vector databases and semantic architectures.

Responsibilities

• Architect and optimize RAG pipelines using vector databases and semantic indexing systems.
• Deploy and configure custom LLMs and embeddings parameters.
• Build backend APIs (FastAPI/Python) to route agent parameters and manage sessions.

Skills

Python proficiency

LLM parameter tuning

RAG pipeline design

Education

Bachelor's or Master's in CS/DS

Tools

Python

LangChain

LlamaIndex

PyTorch

Hugging Face

FastAPI

Pinecone

Chroma

pgvector

Job description

Back to Open Positions

Data & AI

GenAI / AI Engineer

Full-Time Hyderabad, India (Offshore) Posted 6/23/2026

Primary Technology Stack

PythonPyTorchLLMs (GPT/Claude)LangChainVector Databases (Pinecone/Chroma)FastAPI

About The Role

We are hiring two Generative AI Engineers to build intelligent features, orchestrate model pipelines, and implement production-grade AI features. You will design retrieval-augmented generation (RAG) structures, fine-tune models, and deploy high-performance endpoints.

Key Responsibilities

• Architect and optimize RAG pipelines utilizing vector databases and semantic indexing systems.
• Deploy and configure custom large language models (LLMs) and embeddings parameters.
• Build backend APIs (FastAPI/Python) to route agent parameters, manage sessions, and stream outputs.
• Track and mitigate model issues, minimizing errors, prompt injections, and token costs.
• Collaborate with product squads to identify, design, and validate AI enablement opportunities.

Required Qualifications

• 4+ years of software engineering experience, with 2+ years dedicated to AI/ML model integrations.
• Proficient in Python, including libraries like LangChain, LlamaIndex, PyTorch, and Hugging Face.
• Experience configuring and querying production vector databases (Pinecone, Chroma, pgvector).
• Practical experience managing LLM parameters, chunking logic, and semantic architectures.
• Masters or Bachelors in Computer Science, Data Science, or related engineering focus.