Role Overview
As an AI Engineer, you’ll be part of a next-generation engineering team building intelligent, autonomous systems that combine Machine Learning, Large Language Models (LLMs), and Agentic reasoning frameworks. You’ll participate end-to-end — from data ingestion and model training to Retrieval-Augmented Generation (RAG), agent orchestration, and deployment of scalable microservices. This role demands curiosity, precision, and a passion for bridging traditional ML and modern LLM-based agentic architectures into production-grade systems.
Key Responsibilities
- Design and implement RAG pipelines for large-scale data retrieval and contextual reasoning.
- Build, train, and fine-tune ML models using Scikit-learn, TensorFlow, or PyTorch for structured and unstructured datasets.
- Develop modular AI microservices (FastAPI/Flask) integrated with vector databases (FAISS, ChromaDB, Elasticsearch) and embedding pipelines.
- Orchestrate multi-agent systems using LangGraph, LangChain, or Model Context Protocol (MCP) for dynamic task execution.
- Integrate and evaluate LLM APIs (OpenAI, Azure OpenAI, Groq, Anthropic, etc.) for reasoning, generation, and workflow automation.
- Implement data and ML pipelines (Airflow, ZenML, Dagster) for training, evaluation, and inference.
- Develop and expose REST or WebSocket APIs for model and agent communication.
- Apply prompt engineering and reranking strategies to improve contextual accuracy and system reasoning.
- Work closely with data, backend, and AI engineers to deploy, scale, and monitor intelligent microservices in test/staging environments.
- Contribute to shared AI infrastructure modules, ensuring reproducibility, maintainability, and performance.
- Research and prototype new architectures, including multimodal RAG, structured reasoning, or fine-tuning pipelines.
Required Technical Skills
- Strong understanding of RAG architecture — document chunking, embedding, retrieval, reranking, and synthesis.
- Proficiency in Python, including libraries like Pandas, Numpy, and Scikit-learn.
- Experience with FastAPI or Flask for microservice and API development.
- Hands-on with LangGraph, LangChain, or MCP for multi-agent orchestration.
- Familiarity with vector databases (FAISS, ChromaDB, Weaviate, Elasticsearch).
- Good Working knowledge of ML/DL frameworks (TensorFlow, PyTorch).
- Understanding of model serving via REST APIs, batch jobs, or pipelines.
- Exposure to containerization (Docker) and scalable architecture patterns.
- Familiarity with Git, MLflow, or DVC for versioning, tracking, and collaboration.
- Awareness of cloud AI/ML services (Azure ML, AWS SageMaker, GCP Vertex AI).
- Understanding of prompt evaluation, retrieval accuracy metrics, and contextual reasoning benchmarks.
- Curiosity to explore Agentic AI frameworks and autonomous reasoning systems.
- Analytical mindset with a focus on debugging, optimization, and scalability.
- Strong communication and documentation skills for collaborative workflows.
- Innovative and research-driven approach toward new AI architectures.
