GenAI/ Engineer

TechNET; India; Remoto; INR 4.000.000 - 6.500.000; Part-time

Descrizione del lavoro

TechNET is seeking a Senior GenAI Engineer to design and deploy production-grade AI applications, focusing on RAG pipelines, LangChain/LangGraph integration, and agentic workflows. Remote (India) contract role with 4–10 years experience, 6+ months duration.

Role requires deep hands-on experience with LLMs, vector databases, cloud deployment (AWS/Azure), and strong REST API skills. You will collaborate with cross-functional teams to deliver enterprise-grade AI solutions.

Competenze

• Hands-on experience building production-grade Generative AI applications.
• Proven ability to design and deploy RAG pipelines with vector databases and enterprise data sources.
• Experience deploying AI solutions in cloud environments (AWS/Azure).
• Strong knowledge of REST APIs, Git and CI/CD.
• Experience with MLOps/LLMOps, monitoring, and observability.

Mansioni

• Design, develop, and deploy production-grade Generative AI applications.
• Build RAG pipelines using LLMs, vector databases, and enterprise data sources.
• Develop Agentic AI workflows using LangChain, LangGraph, or similar frameworks.
• Integrate LLMs with APIs, databases, and enterprise tools.
• Develop scalable Python services and APIs for AI applications.
• Implement prompt engineering, model evaluation, and quality optimization.
• Deploy, monitor, and troubleshoot AI apps in cloud environments.
• Contribute to MLOps/LLMOps, CI/CD, observability, and production support.
• Collaborate with engineering, product, data, and business teams.

Conoscenze

LLMs & Generative AI

RAG & Prompt Engineering

Agentic AI

LangChain / LangGraph

Vector Databases

Cloud Platforms (AWS/Azure)

REST APIs

MLOps / LLMOps

Python

CI/CD

Formazione

Bachelor's degree in CS/Math/EE/related

Strumenti

LangChain

LangGraph

OpenAI / Azure OpenAI / Bedrock

Descrizione del lavoro

Senior GenAI Engineer – Python | RAG | Agentic AI - Remote.

Experience: 4-10 Years

Location: Remote – India

Engagement: Contract

Duration: 6+ months, with possibility of extension

About the Role

We are looking for a GenAI / AI Engineer with strong hands-on experience building and deploying production-grade Generative AI applications for enterprise environments.

Key Skills

• Hands-on experience with LLMs and Generative AI
• Strong experience with RAG and Prompt Engineering
• Experience building Agentic AI solutions
• Hands-on experience with LangChain / LangGraph
• Experience with Vector Databases and enterprise knowledge retrieval
• Experience with OpenAI / Azure OpenAI / AWS Bedrock or equivalent LLM platforms
• Experience deploying AI applications on AWS or Azure
• Strong knowledge of REST APIs, Git, and CI/CD
• Experience with MLOps / LLMOps, evaluation, monitoring, and observability

Responsibilities

• Design, develop, and deploy production-grade Generative AI applications.
• Build RAG pipelines using LLMs, vector databases, and enterprise data sources.
• Develop Agentic AI workflows using LangChain, LangGraph, or similar frameworks.
• Integrate LLMs with APIs, databases, enterprise applications, and external tools.
• Develop scalable Python services and APIs for AI applications.
• Implement prompt engineering, model evaluation, and response-quality optimization.
• Deploy, monitor, and troubleshoot AI applications in cloud environments.
• Contribute to MLOps/LLMOps, CI/CD, observability, and production support.
• Collaborate with engineering, product, data, and business teams.

Required Stack

Python | LLMs | Generative AI | RAG | Prompt Engineering | Agentic AI | LangChain/LangGraph | Vector Databases | AWS/Azure | REST APIs