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 Description

We 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 Responsibilities

Development

- Design and implement LLM-based pipelines, including:
- Prompt engineering
- Few-shot and zero-shot techniques
- Function/tool calling
- Chain-of-thought and structured output generation
- Work with Azure OpenAI, GPT-4, and embedding models for various use cases
- Build conversational flows, decision trees, and fallback logic for copilots or assistants

Retrieval-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 Weaviate
- Evaluate grounding accuracy and relevance scoring

Machine 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 Integration

- Integrate structured data APIs, SQL endpoints, Power BI connectors, and OLAP cube access as tools/functions callable by the LLM
- Design input/output schemas for safe and deterministic API usage by the model
- Support plugin-style orchestration (LangChain/Function Calling/Semantic Kernel)

Evaluation & Iteration

- Define custom evaluation frameworks using metrics like:
- Hallucination rate
- Grounding precision/recall
- Prompt latency and token efficiency
- Set up experiment tracking using tools like MLflow, Weights & Biases, or PromptLayer
- Maintain few-shot/test prompt sets and continuously refine

Required Skills and Experience

- 3–6+ years of experience in AI/ML/NLP engineering
- Deep familiarity with LLM systems: prompt tuning, orchestration, and fine-tuning
- Hands-on experience with:
- Azure OpenAI Service
- LangChain, Semantic Kernel, or similar orchestration tools
- Vector 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 services
- Experience building and deploying backend components (e.g. FastAPI, Flask) to serve AI models or integrate with retrieval pipelines
- Familiarity 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 APIs

Experience in building chatbots or copilots in enterprise settings

- Knowledge of Azure cloud services, esp. Functions, App Services, Blob Storage, and Key Vault
- Familiarity with enterprise systems like Power BI, SAP, or OLAP cubes

Location

· Bangalore