Agentic AI Engineer

Company Description Acronotics Limited specializes in modern-age automation technologies such as Robotic Process Automation (RPA) and Artificial Intelligence (AI). We apply human intelligence to build cutting-edge robotic automation and AI solutions for our clients, transforming the way businesses operate. Our mission is to help clients design, develop, implement, and run truly transformative generative AI-based solutions.Role DescriptionWe are looking for a  skilled AI/ML Engineer  to help design and implement  GenAI-based systems  that interface with real-time enterprise data. You will be responsible for developing, fine-tuning, orchestrating, and integrating  LLM-powered capabilities  such as retrieval-augmented generation (RAG), function/tool calling, and data-grounded Q&A, within the  Azure OpenAI ecosystem .The ideal candidate brings hands-on experience with  LLM orchestration frameworks , prompt engineering, embedding models, and integrating AI systems into production-grade Azure-based platforms.Core ResponsibilitiesDevelopmentDesign and implement  LLM-based pipelines , including:Prompt engineeringFew-shot and zero-shot techniquesFunction/tool callingChain-of-thought and structured output generationWork with  Azure OpenAI ,  GPT-4 , and embedding models for various use casesBuild conversational flows, decision trees, and fallback logic for copilots or assistantsRetrieval-Augmented Generation (RAG)Develop and optimize  RAG pipelines :Create embedding pipelines (e.g., using text-embedding-ada-002, Cohere, or Sentence Transformers)Chunk and index content from structured and unstructured sources (PDFs, Office files, HTML, etc.)Store and retrieve embeddings using  Azure AI Search ,  FAISS , or  WeaviateEvaluate grounding accuracy and relevance scoringMachine Learning Models Build, train, and fine-tune  time series forecasting models  (e.g., XGBoost, Prophet, ARIMA, or LSTM) for financial KPIs where GenAI requires predictive context Combine  structured model outputs with LLM reasoning  (e.g., forecasts + narrative insights)Tool/Function IntegrationIntegrate structured data APIs, SQL endpoints, Power BI connectors, and OLAP cube access as  tools/functions  callable by the LLMDesign input/output schemas for safe and deterministic API usage by the modelSupport plugin-style orchestration (LangChain/Function Calling/Semantic Kernel)Evaluation & IterationDefine custom  evaluation frameworks  using metrics like:Hallucination rateGrounding precision/recallPrompt latency and token efficiencySet up experiment tracking using tools like  MLflow ,  Weights & Biases , or  PromptLayerMaintain few-shot/test prompt sets and continuously refineRequired Skills and Experience3–6+ years of experience in AI/ML/NLP engineeringDeep familiarity with  LLM systems : prompt tuning, orchestration, and fine-tuningHands-on experience with:Azure OpenAI ServiceLangChain ,  Semantic Kernel , or similar orchestration toolsVector databases  (Azure AI Search, FAISS, Pinecone)Embedding model APIs (OpenAI, HuggingFace, Cohere, etc.)Strong understanding of  time series modeling and ML forecasting techniques  in financial domains (e.g., cost, margin, working capital, price volatility)Strong proficiency in  Python , with experience in developing modular, testable code for AI/ML pipelines, API integrations, and backend servicesExperience building and deploying  backend components  (e.g. FastAPI, Flask) to serve AI models or integrate with retrieval pipelinesFamiliarity with best practices for  production-grade AI applications , including logging, monitoring, and containerisation (e.g. Docker)Ability to work across the full stack of an AI system – from model development to integration and inference APIsExperience in building chatbots or copilots in enterprise settingsKnowledge of  Azure cloud services , esp.  Functions ,  App Services ,  Blob Storage , and  Key VaultFamiliarity with enterprise systems like  Power BI ,  SAP , or  OLAP cubesLocation· Bangalore