AI Engineer (LLM)
Engineering Gandhinagar3–4 yrs experience
The client is looking for a skilled AI Engineer with hands-on experience in Artificial Intelligence, Large Language Models (LLMs), and Generative AI to develop intelligent automation capabilities for our accounting products.
You will develop production-ready AI solutions—including intelligent chat systems, contextual information extraction, Retrieval-Augmented Generation (RAG), AI agents, and automated workflows—to build an intelligent AI layer that enhances automation, accuracy, and decision-making across our applications.
Key Responsibilities
Design, develop, and deploy AI/LLM-powered applications using Python.
Build and optimize RAG pipelines using embeddings, vector search, hybrid search, and reranking.
Integrate open-source and commercial LLMs into production applications.
Develop AI agents and workflows using LangChain, LangGraph, or similar frameworks.
Implement document classification, information extraction, and validation workflows for PDF and OCR-based documents.
Integrate AI services with REST APIs, databases, and cloud-based applications.
Work with OpenSearch, Elasticsearch, or other vector databases for semantic and keyword search.
Deploy and maintain AI services using Docker and AWS.
Evaluate model accuracy, retrieval quality, hallucinations, response latency, and operational costs.
Write unit tests, troubleshoot production issues, and continuously improve AI solution reliability.
Collaborate with software engineers, product teams, and QA engineers to deliver production-grade AI features.
Design, develop, and deploy AI/LLM-powered applications using Python.
Build and optimize RAG pipelines using embeddings, vector search, hybrid search, and reranking.
Integrate open-source and commercial LLMs into production applications.
Develop AI agents and workflows using LangChain, LangGraph, or similar frameworks.
Implement document classification, information extraction, and validation workflows for PDF and OCR-based documents.
Integrate AI services with REST APIs, databases, and cloud-based applications.
Work with OpenSearch, Elasticsearch, or other vector databases for semantic and keyword search.
Deploy and maintain AI services using Docker and AWS.
Evaluate model accuracy, retrieval quality, hallucinations, response latency, and operational costs.
Write unit tests, troubleshoot production issues, and continuously improve AI solution reliability.
Collaborate with software engineers, product teams, and QA engineers to deliver production-grade AI features.
Required Skills and Qualifications
3+ years of experience in Python development and AI/ML engineering.
Hands-on experience building applications using LLMs and Generative AI.
Strong understanding of prompt engineering, structured outputs, and LLM integration.
Practical experience implementing RAG pipelines and embedding-based search.
Experience with LangChain, LangGraph, or equivalent LLM orchestration frameworks.
Knowledge of vector databases or search engines such as OpenSearch, Elasticsearch, or Qdrant.
Experience developing REST APIs using FastAPI, Flask, or similar frameworks.
Familiarity with Docker, AWS, Git, and CI/CD practices.
Understanding of SQL databases, data processing, testing, and application debugging.
Strong problem-solving and analytical skills.
3+ years of experience in Python development and AI/ML engineering.
Hands-on experience building applications using LLMs and Generative AI.
Strong understanding of prompt engineering, structured outputs, and LLM integration.
Practical experience implementing RAG pipelines and embedding-based search.
Experience with LangChain, LangGraph, or equivalent LLM orchestration frameworks.
Knowledge of vector databases or search engines such as OpenSearch, Elasticsearch, or Qdrant.
Experience developing REST APIs using FastAPI, Flask, or similar frameworks.
Familiarity with Docker, AWS, Git, and CI/CD practices.
Understanding of SQL databases, data processing, testing, and application debugging.
Strong problem-solving and analytical skills.
Good to Have
Experience deploying open-source LLMs using vLLM or similar inference frameworks.
Knowledge of models such as Gemma, Llama, or other open-weight LLMs.
Experience with AI agents, tool calling, and workflow orchestration.
Experience with OCR, PDF processing, document classification, and structured data extraction.
Knowledge of fine-tuning techniques, model quantization, and inference optimization.
Experience with accounting, financial documents, audit automation, or compliance-related applications.
Basic understanding of DocumentDB/MongoDB
Experience deploying open-source LLMs using vLLM or similar inference frameworks.
Knowledge of models such as Gemma, Llama, or other open-weight LLMs.
Experience with AI agents, tool calling, and workflow orchestration.
Experience with OCR, PDF processing, document classification, and structured data extraction.
Knowledge of fine-tuning techniques, model quantization, and inference optimization.
Experience with accounting, financial documents, audit automation, or compliance-related applications.
Basic understanding of DocumentDB/MongoDB
Apply for this role
Fill in your details and attach your resume.