Gen AI ENGINEER

Weekday AI (YC W21); Pune District; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

Weekday AI (YC W21) seeks a hands‑on AI engineer to transform Generative AI technologies into seamless user experiences. You will design and deploy agentic apps powered by LLMs and RAG pipelines, integrating with responsive frontends.

Responsibilities include building intelligent interactions with LLMs, optimizing RAG pipelines, and embedding AI capabilities into products alongside backend teams. 3+ years of experience preferred.

Qualifications

• Strong expertise in LLMs, prompt engineering, and transformer models.
• Hands-on experience with RAG architectures, vector search, and embedding models.
• Proficiency in Python and libraries such as LangChain, Transformers, OpenAI SDK, or Hugging Face.
• Familiarity with agentic frameworks like AutoGen, OpenAI, CrewAI, or LangGraph.
• Experience deploying AI models via APIs or microservices.

Responsibilities

• Architect and implement Generative AI solutions leveraging LLMs such as GPT, Claude, and LLaMA to deliver intelligent, human‑like interactions.
• Develop and optimize RAG pipelines using vector databases (ChromaDB for local development and Data-bricks Mosaic ML Vector Stores) to enable efficient knowledge retrieval.
• Build and maintain agentic workflows and conversational AI agents using frameworks like LangGraph and OpenAI, ensuring scalable and adaptive behavior.
• Perform vectorization and fine‑tuning with models such as GTE‑large and BGE to enhance accuracy and contextual relevance.
• Collaborate with backend and app teams to embed Generative AI capabilities into products, ensuring seamless integration and performance.

Skills

LLMs

RAG architectures

Vector search

Embedding models

Python

LangChain

Transformers

OpenAI SDK

Hugging Face

Education

Bachelor’s or Master’s in CS/AI

Tools

LangChain

Transformers

OpenAI SDK

Hugging Face

AutoGen

LangGraph

OpenAI

CrewAI

Job description

Job Description:

This role is for one of Weekday’s clients

Min Experience: 3+ years
Location: Bengaluru, pune
JobType: full-time

In this role, you will transform cutting‑edge Generative AI technologies into seamless, intelligent user experiences. You will design and deploy agentic applications powered by LLMs and Retrieval‑Augmented Generation (RAG) pipelines, while ensuring smooth integration with responsive frontend interfaces.

Key Responsibilities

• Architect and implement Generative AI solutions leveraging LLMs such as GPT, Claude, and LLaMA to deliver intelligent, human‑like interactions.
• Develop and optimize RAG pipelines using vector databases (ChromaDB for local development and Data-bricks Mosaic ML Vector Stores) to enable efficient knowledge retrieval.
• Build and maintain agentic workflows and conversational AI agents using frameworks like LangGraph and OpenAI, ensuring scalable and adaptive behavior.
• Perform vectorization and fine‑tuning with models such as GTE‑large and BGE to enhance accuracy and contextual relevance.
• Collaborate with backend and app teams to embed Generative AI capabilities into products, ensuring seamless integration and performance.

Required Skills & Experience

• Strong expertise in LLMs, prompt engineering, and transformer architectures, applying them to real‑world applications.
• Hands‑on experience with RAG architectures, vector search, and embedding models to build intelligent retrieval systems.
• Proficiency in Python and libraries such as LangChain, Transformers, OpenAI SDK, or Hugging Face for rapid prototyping and deployment.
• Familiarity with agentic frameworks like AutoGen, OpenAI, CrewAI, or LangGraph to design autonomous workflows.
• Experience in deploying AI models via APIs or microservices, ensuring scalability and reliability.

Preferred Skills

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or related fields.
• Practical experience with cloud platforms (AWS, GCP, Azure) to deploy and scale AI solutions.
• Knowledge of CI/CD pipelines to automate testing, deployment, and monitoring of AI services.

Must-have skills

Retrieval Augmented Generation, LLM, Gen Ai

Good-to-have skills

agentic workflows, Python

Requirements: