AI ML Engineer

Position AI Engineer Experience 3+ years Opening(s) 5 Duration Full-time Location Hyderabad Job brief About The Role: We are looking for a motivated and handson AI Engineer with around 3 years of experience to join our growing AI team. In this role, you will help build and ship realworld Generative AI applications, including intelligent assistants, RAG pipelines, and agentic workflows, in a collaborative and fastpaced product environment. This is a builders role. You will be expected to write clean Python backend code, integrate LLMs into production systems, and work closely with product, QA, and DevOps teams to take features from prototype to deployment. Key Responsibilities Build and maintain Pythonbased backend services powering AIdriven features Develop Generative AI applications using LLMs such as GPT models, Claude, and opensource alternatives Implement and optimize RAG pipelines, including chunking, embedding, retrieval, and reranking Build AI agents and toolcalling workflows using frameworks such as LangChain, LangGraph, or similar libraries Design and develop REST APIs to expose AI capabilities to frontend and internal systems Integrate thirdparty AI APIs, vector databases, and model inference endpoints Deploy, monitor, and maintain applications on AWS using services such as EC2, S3, Lambda, and related tooling Write modular, testable, and productionready code, and participate in code reviews Collaborate with product managers, QA engineers, and DevOps teams to deliver scalable and reliable AI solutions Help improve system quality through evaluation, debugging, monitoring, and performance optimization Required Skills 3+ years of handson experience in Python backend development Working experience building LLMpowered applications such as chatbots, assistants, document Q&A systems, or workflow copilots Handson experience with LangChain, LangGraph, or similar orchestration frameworks Solid understanding of RAG architecture, including embeddings, vector search, semantic retrieval, and ranking strategies Familiarity with vector databases such as FAISS, Weaviate, Pinecone, or Chroma Experience with OpenAI API, Hugging Face, or similar model ecosystems Practical knowledge of prompt engineering for reasoning, tool use, structured outputs, and taskspecific workflows Experience building REST APIs using FastAPI or Flask Working knowledge of AWS services such as EC2, S3, Lambda, and deployment workflows Comfort working in Linux/Unix environments, using Git, and writing clean, maintainable code Good to Have Exposure to opensource LLMs such as LLaMA, Mistral, qwen, Deepseek or similar models, including local inference setups Familiarity with Docker and containerized deployments Basic understanding of MLOps / LLMOps, including experiment tracking, prompt versioning, evaluation, and monitoring Exposure to multiagent systems or autonomous workflow design Experience with CI/CD pipelines and staging/production deployment practices Prior work with PyTorch or TensorFlow for finetuning or experimentation About our Company The Dollar Business is the only multifeatured platform on foreign trade in India (www.thedollarbusiness.com). We are a technology company with its headquarters in Hyderabad and regional offices in New Delhi, Ahmedabad, and Chennai. Our cloudbased technology service offering is EXIMAPS, which is modelled as a Platform as a Service (PaaS/SaaS) product. It is powered by a proprietary engine based on a triad of Foreign Trade Information, Human knowledge, and Machine learning (AI). Position AI Engineer Experience 3+ years Opening(s) 5 Duration Full-time Location Hyderabad Job brief About The Role: We are looking for a motivated and handson AI Engineer with around 3 years of experience to join our growing AI team. In this role, you will help build and ship realworld Generative AI applications, including intelligent assistants, RAG pipelines, and agentic workflows, in a collaborative and fastpaced product environment. This is a builders role. You will be expected to write clean Python backend code, integrate LLMs into production systems, and work closely with product, QA, and DevOps teams to take features from prototype to deployment. Key Responsibilities Build and maintain Pythonbased backend services powering AIdriven features Develop Generative AI applications using LLMs such as GPT models, Claude, and opensource alternatives Implement and optimize RAG pipelines, including chunking, embedding, retrieval, and reranking Build AI agents and toolcalling workflows using frameworks such as LangChain, LangGraph, or similar libraries Design and develop REST APIs to expose AI capabilities to frontend and internal systems Integrate thirdparty AI APIs, vector databases, and model inference endpoints Deploy, monitor, and maintain applications on AWS using services such as EC2, S3, Lambda, and related tooling Write modular, testable, and productionready code,