Gen AI Engineer

Role: Gen AI Jr role

Location: USA

Client: Deloitte

About the Role

We are looking for a passionate Gen AI Junior Engineer to join our growing AI team. This role is ideal for someone eager to build real-world applications powered by Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agentic AI systems.

You will work on designing, developing, and optimizing AI-driven applications using modern GenAI frameworks, APIs, and cloud-based AI services such as Azure AI Foundry and OpenAI technologies.

Key Responsibilities

Develop and deploy LLM-powered applications using Python.

Design and implement Agentic AI workflows (multi-step reasoning, tool usage, memory handling).

Build and optimize Prompt Engineering strategies for accuracy, cost-efficiency, and reliability.

Manage token usage and cost optimization for production-grade AI systems.

Implement RAG (Retrieval-Augmented Generation) pipelines using vector databases.

Work with embeddings, chunking strategies, and semantic search.

Integrate AI models using REST APIs and SDKs.

Build and test AI services using Azure OpenAI Service.

Develop proof-of-concepts using frameworks like:

LangChain

Semantic Kernel

Model Context Protocol

Work with vector databases (e.g., Azure AI Search, Pinecone, etc.).

Collaborate with frontend teams to integrate AI into UI frameworks (React/Streamlit/Gradio).

Continuously evaluate and experiment with emerging GenAI tools and frameworks.

Required Skills & Qualifications

Bachelor’s degree in computer science, AI, Data Science, or related field.

Strong proficiency in Python.

Understanding of:

Large Language Models (LLMs)

Transformers basics

Embeddings and semantic similarity

Tokenization concepts

Experience working with APIs (REST, JSON).

Familiarity with:

LangChain or Semantic Kernel

Azure OpenAI Service or OpenAI APIs

Vector databases (Azure AI Search, Pinecone, FAISS, etc.)

Basic knowledge of RAG architecture and prompt optimization.

Understanding of token cost management and inference optimization.

Strong problem-solving and debugging skills.

Eagerness to learn and experiment with GenAI ecosystems.

Nice-to-Have

Exposure to multi-agent systems and agent orchestration.

Knowledge of fine-tuning techniques.

Experience with UI frameworks (React, Streamlit, Gradio).

Familiarity with cloud environments (Azure preferred).

Basic DevOps knowledge (Docker, CI/CD).

What You’ll Gain

Hands-on experience building production-grade AI systems.

Exposure to cutting-edge Agentic AI architectures.

Opportunity to work with enterprise AI platforms like Azure AI Foundry.

Mentorship and learning opportunities in advanced LLM systems.

A fast-paced innovation-driven environment.