Job Description

Location:

Hyderabad, India

Company:

Radise India

Type:

Full-Time | On-site

Experience:

2-5 years (Mid-Level); open to strong junior candidates with relevant project experience

About the Role:

RADISE India is a growing Civil Engineering firm in Asia Pacific (APAC) Market using innovative IoT-based sensor technology aimed at providing infrastructure owners, builders, and operators the vital information on structural behavior to help them reduce the uncertainties associated with material properties and structural capacity. RADISE India, provides a wide range of innovative engineering consulting services for infrastructure owners, builders, contractors, vendors, and operators. Our technology driven products and services are for infrastructure builders, owners & operators, government bodies, general contracting firms.

Key Responsibilities:

Evaluate and deploy

open-source LLMs

(Gemma, DeepSeek, LLaMA 3, Mistral, etc.) for use in document Q&A, natural language to SQL translation, and AI-driven insights. Implement

document ingestion pipelines

(PDF, Word, Excel, images) using tools like LangChain, Haystack, or LlamaIndex for chunking, embedding, and vector search. Set up and manage

vector databases

(e.g., pgvector). Develop

RAG pipelines

to connect embeddings from Azure Blob Storage files and PostgreSQL data. Build and test

AI agents

capable of routing user queries to either blob-based document retrieval or database querying (SQL generation).

Engineer and Evaluate prompts

by implementing industry standard prompt engineering techniques. Work closely with our backend team (TypeScript, Express, PostgreSQL) to expose AI capabilities as services or APIs. Benchmark cost, performance, and latency of different models and infrastructures. Support future transition to secure/compliant deployment models (FedRAMP, NIST 800-171). Collaborate with the product team to refine chat UX and identify high-impact use cases.

Required Skills and Qualifications:

Bachelor's or Master's in Computer Science, AI/ML, Data Science, or related field. 2+ years of hands-on experience working with

LLMs

, embeddings, or NLP pipelines. Solid understanding of

open-source AI stacks

(Transformers, LangChain, LlamaIndex, etc.). Familiarity with

vector databases

and semantic search principles. Experience working with

Python

and optionally some

TypeScript/Node.js

. Comfortable working with

SQL

and relational databases like PostgreSQL. Strong understanding of

AI infrastructure

(Docker, Linux, GPU/CPU optimization, cloud deployment - Azure preferred). Must have Strong Prompt Engineering skills. Ability to read and implement research papers or GitHub repos for LLM-based applications.

Preferred (Nice-to-Have):

Experience deploying or fine-tuning

OpenAI,

LLaMA, Mistral, Falcon

, or similar open-source models. Familiarity with

Azure OpenAI, Azure Cognitive Search, or OpenAI APIs

for benchmarking. Experience with OCR tools and document parsing pipelines. Exposure to

civil engineering or construction domain data

is a plus.

Why Join Us?

Work on cutting-edge AI applications for infrastructure and civil engineering - real-world impact. Direct mentorship from leadership (with deep engineering expertise) and cross-functional collaboration. Opportunity to experiment with and deploy models at scale across enterprise SaaS. Growth potential to lead AI initiatives across multiple product lines (SmartInfra Hub, SmartCompose.AI, etc.).
Job Type: Full-time

Pay: ?800,000.00 - ?2,000,000.00 per year

Benefits:

Health insurance Paid sick time Paid time off Provident Fund
Schedule:

Day shift Monday to Friday
Experience:

AI Engineer: 3 years (Preferred)
Location:

Hyderabad, Telangana (Required)
Work Location: In person