AI Engineer | LLM Applications & Agentic AI

Company: Finarb Analytics Consulting Pvt. Ltd. Job Title: AI Engineer | LLM Applications & Agentic AI Location: Hyderabad / Kolkata Experience: 2–5 Years Employment Type: Full-Time Work Mode: On-site / Hybrid About Finarb Finarb is a data science, AI, and technology consulting firm that helps businesses solve complex problems through advanced analytics, machine learning, and intelligent automation. We work with global clients across healthcare, financial services, private equity, and other industries, developing solutions that combine data engineering, predictive modeling, generative AI, and enterprise applications. Our work spans traditional machine learning and deep learning to emerging areas such as large language models, agentic AI, and decision intelligence. We focus on building practical, scalable solutions that deliver measurable business value. About the Role We are looking for an AI Engineer with strong Python skills and hands-on experience building applications using Large Language Models (LLMs), RAG, and agentic AI frameworks. The role involves designing and developing AI applications that can reason over enterprise data, interact with tools and APIs, execute multistep workflows, and integrate with existing business systems. We are particularly interested in engineers who understand the fundamentals of machine learning and data engineering, rather than just working with LLM APIs. You should be comfortable taking an AI application from initial development through testing, evaluation, and production deployment. Key Responsibilities Design, develop, and deploy LLM-powered applications using OpenAI, Claude, Gemini, and open-source models. Build agentic AI systems using LangChain, LangGraph, and similar frameworks, including tool calling, planning, state management, and multi-agent orchestration. Develop reusable agent tools and skills that can be chained together to execute complex analytical and business workflows. Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including document processing, chunking, embeddings, vector search, and reranking. Integrate AI applications with databases, APIs, enterprise systems, and external tools, including MCP-based integrations. Develop backend services and APIs using Python and FastAPI. Design evaluation frameworks to measure LLM response quality, retrieval accuracy, agent reliability, and overall application performance. Implement appropriate guardrails, error handling, logging, and monitoring for production AI systems. Optimize applications for accuracy, latency, scalability, and inference costs. Work closely with data engineers, data scientists, and software developers to build and deploy AI solutions. Required Skills & Experience 2–5 years of experience in software engineering, machine learning, or AI application development, including hands-on LLM application development. Strong programming skills in Python, including object-oriented programming, asynchronous processing, and API development. Practical experience with LangChain, LangGraph, or comparable orchestration frameworks such as LlamaIndex, CrewAI, or AutoGen. Experience building agentic workflows involving tool/function calling, state management, memory, and multistep execution. Experience developing RAG applications, working with embeddings, and integrating vector databases. Strong understanding of SQL, data processing, data pipelines, and data quality. Working knowledge of machine learning fundamentals, including model training, evaluation, overfitting, and common failure modes. Understanding of transformer architectures, LLM capabilities, and limitations. Familiarity with statistical concepts such as distributions, sampling, hypothesis testing, and A/B testing. Experience developing REST APIs using FastAPI or similar Python frameworks. Good understanding of software engineering practices, Git, testing, and debugging. Good to Have Experience with vector databases such as pgvector, Pinecone, Qdrant, Weaviate, or Azure AI Search. Knowledge of advanced RAG techniques, including hybrid search, reranking, and agentic retrieval. Experience with PyTorch, Hugging Face Transformers, and open-source LLMs. Familiarity with fine-tuning techniques such as LoRA and QLoRA. Experience with Model Context Protocol (MCP) and developing integrations with external tools. Familiarity with LLM evaluation and observability tools such as LangSmith, Langfuse, Ragas, or Braintrust. Experience with Azure OpenAI, AWS Bedrock, or Google Vertex AI. Knowledge of Docker, CI/CD pipelines, and cloud deployment. Understanding of AI security, prompt injection, guardrails, and responsible AI practices. Experience optimizing LLM inference through model selection, caching, and routing. What We're Looking For We value engineers who can think beyond prompts and frameworks. You should understand how the underlying data, models, and application components work together and be able to make sensible technical decisions. You should be comfortable experimenting with new approaches, evaluating results objectively, debugging complex workflows, and building systems that remain reliable outside controlled demonstrations. Experience building and deploying real-world AI applications will be valued more than certifications or familiarity with a long list of frameworks. Why Join Finarb? Work on challenging AI projects involving LLMs, agentic systems, machine learning, and enterprise data. Build production applications for global clients across multiple industries. Experiment with proprietary and open-source AI models and emerging frameworks. Work across the complete development lifecycle, from architecture and prototyping to production deployment. Collaborate with experienced data scientists, AI engineers, and software developers. Take ownership of technical solutions and contribute directly to product development. Location: Hyderabad / Kolkata Experience: 2–5 Years Employment: Full-Time Website: www.finarb.ai