Job description

• Backend Development: Design, develop, and maintain REST APIs using Python to integrate AI/ML services.
• Agentic AI Development: Design and orchestrate AI agents capable of reasoning, planning, and executing multi-step tasks by integrating LLMs with APIs, tools, and data sources.
• AI/ML Orchestration: Implement and manage machine learning models, large language models (LLMs), Agentic AI workflows and AI orchestration using Python.
• Generative AI Solutions: Using Generative AI models for tasks like text generation, summarization, conversational AI, and content creation.
• Data Management: Work with structured databases (SQL), graph databases (e.g., CosmosDB), and unstructured data stores (e.g., Elasticsearch).
• RAG Implementation: Build retrieval-augmented generation (RAG) pipelines leveraging Azure AI Search, AWS OpenSearch, or other vector databases for contextual responses.
• Data Pipelines: Design and manage robust data ingestion and transformation pipelines to feed AI models.
• Intent Detection & NLU: Develop or integrate intent detection models and natural language understanding (NLU) solutions to enhance conversational AI.
• Prompt Engineering & Optimization: Create and optimize prompts for LLMs to improve response quality and reduce latency.
• AI Integration: Collaborate with frontend and product teams to embed Gen AI features into enterprise applications.

• Backend Development: Proficient in Python for building and maintaining scalable REST APIs, familiarity with integrating AI services.
• AI/ML Orchestration: Strong expertise in Python with a focus on machine learning, large language models (LLMs), AI orchestration.
• Agentic AI Expertise: Experience in building autonomous AI agents using frameworks like OpenAI Functions, or custom orchestration solutions to handle tool use and multi-step reasoning.
• Generative AI Expertise: Generative AI models (text generation, summarization, conversational AI) and applying prompt engineering techniques.
• Data Management: Solid understanding of structured (SQL), graph (CosmosDB), and unstructured (Elasticsearch) databases; ability to design efficient data access patterns for AI workloads.
• RAG Implementation: Proven experience implementing retrieval-augmented generation using Azure AI Search, AWS OpenSearch, or other vector databases.
• Data Pipelines: Hands-on experience building and managing data ingestion and transformation pipelines using Databricks, Azure Data Factory, or equivalent tools.
• Intent Detection & NLU: Skilled in developing or deploying intent detection models and natural language understanding (NLU) components for conversational AI applications.

• Familiarity with cloud platforms such as Azure and AWS.
• Knowledge of additional AI/ML frameworks and tools.
• Knowledge of Agentic AI
• Experience with DevOps practices and CI/CD pipelines.

Skills Required

Key Skills

• AI /ML
• GENAI
• RAG

Other Information