AI Developer - Large Language Models

Volody; Maharashtra; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Volody is seeking an experienced AI Developer to design, build, and deploy LLM-based applications for real-world use cases. You will turn research into production-grade AI systems and collaborate with cross-functional teams.

Responsibilities include implementing RAG pipelines with vector stores, fine-tuning models, and building NLP workflows for classification, summarization, extraction, and search. Proficiency in Python and modern AI tooling is essential.

Qualifications

• 2-7 years of AI/ML development experience.
• Hands-on with LLMs and RAG systems.
• Prior AI-first company/product experience mandatory.

Responsibilities

• Design, build, and deploy LLM-based applications for real-world use cases.
• Implement and optimize RAG pipelines using vector databases and document stores.
• Fine-tune, evaluate, and prompt-engineer LLMs for accuracy and performance.
• Build NLP pipelines for text classification, summarization, extraction, and search.
• Integrate AI models with backend systems and APIs.
• Work with unstructured data (PDFs, docs, emails, chat logs, etc.).
• Monitor model performance, hallucination risks, and response quality.
• Collaborate closely with product, engineering, and data teams.
• Stay updated with the latest AI/LLM research and tooling.

Skills

LLMs

RAG pipelines

NLP concepts

Python

LangChain

LlamaIndex

Hugging Face

Embeddings

Production deployment

AI-first experience

Tools

Pinecone

Weaviate

FAISS

Chroma

Milvus

Job description

Job Description

We are seeking an experienced AI Developer with strong hands-on expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Natural Language Processing (NLP). The ideal candidate must have worked in an AI-first product or company, contributing to real-world, production-grade AI systems.

Key Responsibilities

• Design, build, and deploy LLM-based applications for real-world use cases
• Implement and optimize RAG pipelines using vector databases and document stores
• Fine-tune, evaluate, and prompt-engineer LLMs for accuracy and performance
• Build NLP pipelines for text classification, summarization, extraction, and search
• Integrate AI models with backend systems and APIs
• Work with unstructured data (PDFs, docs, emails, chat logs, etc.)
• Monitor model performance, hallucination risks, and response quality
• Collaborate closely with product, engineering, and data teams
• Stay updated with the latest AI/LLM research and tooling

Required Skills & Qualifications

• 2- 7 years of experience in AI / ML development
• Strong hands-on experience with LLMs (OpenAI, Anthropic, LLaMA, Mistral, etc.)
• Proven experience building RAG systems
• Solid knowledge of NLP concepts and techniques
• Experience with vector databases (Pinecone, Weaviate, FAISS, Chroma, Milvus)
• Proficiency in Python
• Experience with frameworks such as LangChain, LlamaIndex, Hugging Face
• Strong understanding of embeddings, chunking, ranking, and retrieval strategies
• Experience deploying models in production environments
• Mandatory : Prior experience working in an AI-first company or product

Good To Have

• Experience with model fine-tuning (LoRA, PEFT)
• Knowledge of MLOps / LLMOps
• Experience with AWS / GCP / Azure
• Familiarity with evaluation frameworks for LLMs
• Experience building AI agents or autonomous workflows

Soft Skills

• Strong problem-solving and analytical thinking
• Ability to work in fast-paced, ambiguous environments
• Clear communication and documentation skills
• Product-oriented mindset

(ref:hirist.tech)