Senior Artificial Intelligence Engineer

Prohash Technologies; Coimbatore District; Hybride; INR 3 000 000 - 6 000 000; Plein temps

Résumé du poste

Prohash Technologies is seeking two Senior AI Engineers to build enterprise AI applications that connect large language models to business data. You will own the design and build, ensuring accuracy, security and reliability in production.

You will design architecture, implement RAG pipelines, integrate LLM APIs and enterprise systems, and deploy to cloud with a focus on security, latency and cost. This is applied engineering, not research.

Qualifications

• 6–10 years in software development, incl. 2+ years building AI/LLM apps in production.
• Strong Python.
• Hands-on RAG experience: embeddings, semantic search and a vector database (Pinecone, Chroma, FAISS, Weaviate, Milvus or pgvector).
• Production use of LLM APIs — Claude, OpenAI, Amazon Bedrock, Azure OpenAI or OCI Generative AI.
• Proven solution design: you have architected an enterprise integration and can defend it on security, cost and failure handling.
• REST API integration, authentication and authorisation, and safe handling of sensitive data.
• Cloud deployment on AWS, Azure, OCI or GCP, with Docker and CI/CD.
• Daily use of AI coding assistants (Claude Code, Copilot, Cursor), and a clear view of where they fail.

Responsabilités

• Design the architecture — integration, data flow, access control and failure handling.
• Build RAG pipelines so the system answers from approved data, not guesswork.
• Integrate LLM APIs and enterprise systems, and build the application layer around them.
• Use AI coding assistants to build faster, and review everything they produce.
• Deploy to cloud, test for accuracy, and own it in production — security, latency and cost.

Connaissances

Python

RAG (retrieval-augmented generation)

LLM APIs

REST APIs

AI coding assistants

Production AI development

Outils

Pinecone

Chroma

FAISS

Weaviate

Milvus

pgvector

Docker

Description du poste

ABOUT THE ROLE

We are hiring two Senior AI Engineers to build AI applications for enterprise use connecting large language models to business data and making the results accurate, secure and reliable in production.

You will own the design as well as the build: decide how the solution works, then build it using AI coding tools and verify everything that ships. This is applied engineering, not research.

WHAT YOU WILL DO

• Design the architecture — integration, data flow, access control and failure handling.
• Build RAG pipelines so the system answers from approved data, not guesswork.
• Integrate LLM APIs and enterprise systems, and build the application layer around them.
• Use AI coding assistants to build faster, and review everything they produce.
• Deploy to cloud, test for accuracy, and own it in production — security, latency and cost.

MUST HAVE

• 6–10 years in software development, including 2+ years building AI/LLM applications used in production.
• Strong Python.
• Hands-on RAG experience: embeddings, semantic search and a vector database (Pinecone, Chroma, FAISS, Weaviate, Milvus or pgvector).
• Production use of LLM APIs — Claude, OpenAI, Amazon Bedrock, Azure OpenAI or OCI Generative AI.
• Proven solution design: you have architected an enterprise integration and can defend it on security, cost and failure handling.
• REST API integration, authentication and authorisation, and safe handling of sensitive data.
• Cloud deployment on AWS, Azure, OCI or GCP, with Docker and CI/CD.
• Daily use of AI coding assistants (Claude Code, Copilot, Cursor), and a clear view of where they fail.

NICE TO HAVE

• AI agents, tool calling or Model Context Protocol (MCP).
• LangChain or LlamaIndex.
• Single sign-on — Entra ID, SAML or OIDC.
• Insurance, banking or financial services experience.