Back to list

Vacancy description

Generative AI Engineering Intern — Venxr in Pune, भारत

Venxr

Rs 15000 - Rs 20000 per month

Pune, भारत

About Venxr 

Venxr is building AdsGPT, a conversational AI platform that enables brands to plan, execute, and optimise advertising campaigns through natural language. 

We're looking for a curious and hands-on Generative AI Engineering Intern who wants to go beyond basic prompt engineering and learn how to build real-world applications powered by Large Language Models (LLMs). 

If you've experimented with LangChain, LangGraph, MCP, AI agents, or memory systems and enjoy figuring out how things work under the hood, we'd love to hear from you. 

What You'll Work On 

  • Build and improve LLM-powered features for AdsGPT. 

  • Develop AI workflows that help users plan campaigns, retrieve information, and interact with advertising tools. 

  • Experiment with AI agents, tool calling, and multi-step reasoning. 

  • Implement context engineering and memory management to improve the quality of AI responses. 

  • Integrate LLMs with APIs, databases, and external tools. 

  • Test AI-generated outputs, identify failure cases, and improve reliability. 

  • Collaborate with the product and engineering teams to turn ideas into working prototypes and product features. 

Tech Stack 

  • AI/LLMs : Claude and other frontier models, LLM APIs. 

  • AI frameworks: LangChain, LangGraph, or equivalent orchestration frameworks. 

  • AI engineering: MCP, LLM orchestration, context engineering, memory management, and tool calling. 

  • Backend: Python, Django or FastAPI. 

  • Frontend: React.js. 

You don't need to know every technology listed, but you should have a strong interest in AI engineering and practical experience with at least some of these tools. 

What You'll Explore 

We want you to understand how AI applications work beyond sending prompts to a model. 

  • LLM fundamentals: Tokens, context windows, structured outputs, latency, cost, and hallucinations. 

  • AI orchestration : Building workflows with LangChain, LangGraph, or similar frameworks. 

  • Context engineering: Managing what information the model receives, including retrieval, context selection, and context-window optimisation. 

  • Memory management: Maintaining conversational history, state, and relevant information across interactions without unbounded context growth. 

  • AI agents and tool calling : Connecting models to APIs, tools, and external systems. 

  • MCP: Understanding how models interact with external tools and services through the Model Context Protocol. 

  • Evaluation and debugging: Testing AI responses, identifying failure modes, and improving system reliability. 

  • RAG and retrieval : Working with external knowledge sources to generate more relevant responses. 

What We're Looking For 

  • 0–1 year of experience in AI engineering, product development internship, or related projects. 

  • https://jobeax.com/link/2DENLGgQM7whDhaE in AI/ML or CSE. 

  • Good foundational knowledge of Python. 

  • Hands-on experience building at least one GenAI application, AI agent, chatbot, or LLM-powered workflow. 

  • Hands-on experience with LangChain, LangGraph, MCP, or equivalent AI frameworks, with an understanding of LLM orchestration, context engineering, memory management, and tool calling. 

  • Basic knowledge of REST APIs and databases. 

  • Strong problem-solving and debugging skills. 

  • Willingness to experiment, learn quickly, and explain your technical decisions. 

We value practical implementation over certificates. Personal projects, hackathons, academic projects, and open-source contributions count. You should be able to explain what you built, how it works, and what you would improve. 

Good to Have 

  • Experience with RAG, embeddings, vector databases, or semantic search. 

  • Exposure to multi-agent systems and workflow orchestration. 

  • Familiarity with LLM evaluation tools such as LangSmith, Langfuse, or Ragas. 

  • Basic https://jobeax.com/link/6WcBICn0LM558SP0 or frontend development experience. 

  • Familiarity with Git, Docker, cloud deployment, or CI/CD. 

  • Interest in Generative UI, AdTech, or MarTech. 

How We Work 

At Venxr, you'll work on real product challenges alongside the engineering and product teams. You'll have opportunities to experiment with new AI approaches, build prototypes, debug complex workflows, and contribute to features that can make their way into a live product. 

We value curiosity, ownership, thoughtful problem-solving, collaboration, and a willingness to learn from failures. 

We're looking for people who ask questions, take initiative, and enjoy turning ideas into working solutions. 

Selection Process 

  • Technical screening: A 30-minute discussion about your projects, Python fundamentals, and GenAI concepts. 

  • Take-home assignment : Build a small LLM-powered workflow or agent. AI coding tools are welcome, but you must understand and explain your implementation. 

  • Technical interview: Walk us through your solution, design decisions, debugging approach, and potential improvements. 

  • Final round: Technical and managerial discussion. 

How to Apply 

Share your resume along with links to your GitHub, portfolio, or GenAI projects. 

Similar vacancies

More like this role

... civil society, running evaluations on our own platform with native speakers and domain experts across India and beyond. Our benchmarks, leaderboards and reports aim to help model developers and decision-makers understand where models work well and where they fall short. As a Research Engineering Intern, you will work alongside ...

Bangalore, भारत

Client of Fidius Advisory

AI Architect - Generative AI

About the role:Our client is looking for a seasoned AI Architect with deep expertise in cloud-native enterprise systems and Generative AI. You will define and deliver scalable, secure, production-grade GenAI architectures, including multi-agent, RAG, LLMOps and AgentOps systems, and lead cross-functional teams to build ...

Bangalore, भारत

BU Consultants

Generative AI Manager

  • Remote
  • Full-time

Rs 30 - 35 lakhs p.a.

... teams to understand their workflows, identify opportunities and propose effective AI solutions. - Develop and implement AI-powered tools, assistants and custom AI components. - Drive developer productivity and process efficiency through Generative AI adoption. - Enable integration of internal data and services with Large ...

India, भारत

Evnek Technologies Pvt Ltd

Generative AI Engineer

  • Contract
  • AI / ML
... Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Generative AI technologies. Fresh graduates with hands-on AI/GenAI projects or relevant internship experience are encouraged to apply. Key Responsibilities - Develop and implement AI-powered applications using LLMs and Generative AI. - Build and optimize ...

Bangalore, भारत

  • Full-time
... Excellence. Where the AI Engineering & Enablement Lead sets architecture and governance, this role turns that direction into working, production-grade agents and AI workflows that ride on EVERSANA's enterprise AI stack (GCP, Vertex AI, Claude, Gemini Enterprise). This engineer productionizes enterprise AI tooling for Patient ...

Pune, भारत

  • Backend
Python + AI / GenAI - Bangalore / MumbaiExperience : 5 - 12 YearsLocation : BangaloreWork Mode : WFO / HybridKey Skills :- Strong hands-on Python- Generative AI / LLM- RAG, Prompt Engineering, Embeddings- LangChain / LangGraph / LlamaIndex / CrewAI / AutoGen- AI Agents / Agentic AI- REST APIs / FastAPI / Flask / Django- ...

Bombay, भारत

... identify AI opportunities and mentor junior https://jobeax.com/link/bPKH86SZzX87taAc Qualifications :- Bachelor's degree or higher in computer science or engineering.- 10+ years of overall experience, with 7+ years in AI, ML, and/or NLP R&D.- Must have experience in: Clinical Trials, FDA Dossier Preparation, Drug Discovery, ...

Bangalore, भारत

  • Data Science
  • Research
... Develop and manage training and evaluation datasets, including synthetic data generation, annotation pipelines, and benchmark creation.- Collaborate with engineering and product teams to deploy research outputs into scalable systems.- Stay up-to-date with the latest advancements in AI and contribute to internal research ...

Bangalore, भारत

Capgemini Technology Services India Limited

Capgemini - AI/ML Engineer - Generative AI

  • Hybrid
... https://jobeax.com/link/3l8821Zx9658zJon Role : - Develop and enhance Generative AI applications using LLMs and AI frameworks.- Build and optimize RAG pipelines, vector search, and AI-powered workflows.- Design effective prompts and fine-tune models using techniques such as LoRA and QLoRA.- Develop REST APIs and integrate AI capabilities into ...

Calcutta, भारत

  • Full-time
  • Consulting
... https://jobeax.com/link/MPrGoo1PSJpZ7d0e, https://jobeax.com/link/2DENLGgQM7whDhaE or B.E.. What you'll do - Lead the architecture, design, and development of enterprise Agentic AI platforms on AWS What you need - LLMs - AWS - Elasticsearch - DynamoDB - ERP - CRM Good to have - Machine learning Job details - Location: Mumbai - Education: ...

Bombay, भारत