AI Developer

We are looking for a passionate AI/ML Developer with 5+ years of overall experience, including a minimum of 2 years of hands-on experience in Generative AI and Large Language Model (LLM) application development, and at least 1 year of experience in Agentic AI.

The ideal candidate should have strong expertise in Python/TypeScript, RESTful APIs, and LLM orchestration frameworks such as LangChain and LlamaIndex. The candidate should also have experience in prompt engineering, vector databases, cloud AI platforms, Natural Language Processing (NLP), and scalable microservices architecture.

Note: Candidates must have applied the relevant technologies in real-time production projects and be able to demonstrate their implementation experience, architecture, use cases, and business outcomes during the interview.

Key Responsibilities

• Design, develop, and deploy Generative AI and LLM-powered applications.
• Develop scalable backend services using Python and FastAPI.
• Build and integrate RESTful APIs and microservices for AI applications.
• Develop AI-driven backend solutions using Python or TypeScript.
• Build AI solutions using LLM orchestration frameworks such as LangChain, LlamaIndex, or similar frameworks.
• Design and optimise prompts using advanced prompt engineering techniques, including zero-shot, few-shot, Chain-of-Thought (CoT), and function calling.
• Build Retrieval-Augmented Generation (RAG) solutions using vector databases such as Pinecone, ChromaDB, FAISS, or Weaviate.
• Integrate AI applications with cloud AI platforms, including AWS Bedrock, Amazon SageMaker, Azure OpenAI, and Google Vertex AI.
• Apply NLP concepts, embeddings, and transformer models to solve business problems.
• Collaborate with cross-functional teams to deliver scalable, production-ready AI solutions.
• Follow software engineering best practices, including version control using Git, CI/CD pipelines, and technical documentation.

Mandatory Technical Skills

Candidates must have hands-on experience in the following:

• Python
• Generative AI (GenAI)
• Large Language Models (LLMs)
• Prompt Engineering
• FastAPI
• Agentic AI

Preferred Technical Skills

• TypeScript
• LangChain and LlamaIndex
• RESTful API Development
• GraphQL
• Microservices Architecture
• Retrieval-Augmented Generation (RAG)
• Vector Databases: Pinecone, ChromaDB, FAISS, or Weaviate
• Cloud AI Platforms: AWS Bedrock, Amazon SageMaker, Azure OpenAI, or Google Vertex AI
• Natural Language Processing (NLP)
• Embeddings and Transformer Models
• Git and CI/CD Pipelines

Preferred Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related discipline.
• 5+ years of overall professional experience, including:
• A minimum of 2 years of hands-on experience in Generative AI and LLM application development.
• At least 1 year of hands-on experience in Agentic AI.
• Strong analytical, debugging, and problem-solving skills.
• Excellent communication and collaboration skills.
• Ability to independently manage project work and deliver results.
• A passion for AI innovation, continuous learning, and emerging technologies.

Job Type: Full-time

Pay: ₹95,000.00 - ₹150,000.00 per month

Application Question(s):

• How many years of overall experience do you have in software development, Generative AI/LLM application development, and Agentic AI? Please specify the number of years of hands-on experience in each.
• Have you developed and deployed any Generative AI or LLM-powered applications in a live production environment? If yes, briefly describe the use case and the LLM technologies or frameworks you used.
• How would you rate your hands-on experience with Python and FastAPI? Have you used them to develop backend services or REST APIs for AI applications in production?
• Do you have at least 1 year of hands-on experience in Agentic AI? If yes, briefly describe an AI agent or multi-agent solution you have implemented and the tools, frameworks, or orchestration techniques you used.
• Have you worked with LangChain, LlamaIndex, RAG, or vector databases such as Pinecone, ChromaDB, FAISS, or Weaviate? Please specify the technologies you have used in production. Also, are you comfortable with the role's employment terms and joining timeline?

Work Location: In person