Responsibilities

- Build, deploy, and maintain AI-powered applications and intelligent agents

- Develop agentic AI workflows, multi-agent systems, and AI orchestration frameworks

- Design and develop Large Language Model application development and Generative AI solution design

- Integrate both commercial and open-source foundation models

- Develop production-grade applications and APIs using Python

- Develop REST APIs, microservices, and event-driven architectures

- Integrate enterprise data sources, structured and unstructured datasets, and knowledge repositories

- Design enterprise-scale AI platforms and reusable AI services

- Evaluate AI technologies and recommend architecture patterns aligned with business objectives

- Establish engineering standards, reusable frameworks, and best practices for AI solution delivery

Requirements

- Strong experience building, deploying, and maintaining AI-powered applications and intelligent agents

- Expertise in Large Language Model application development and Generative AI solution design

- Experience developing agentic AI workflows, multi-agent systems, and AI orchestration frameworks

- Knowledge of prompt engineering, agent evaluation, guardrails, grounding techniques, and AI application observability

- Familiarity with Retrieval-Augmented Generation, semantic search,



vector databases, and knowledge management architectures

- Hands-on experience with modern AI orchestration frameworks including LangGraph, LangChain, LlamaIndex Hugging Face, Open-Source LLM ecosystems

- Strong proficiency in Python with experience building production-grade applications and APIs

- Experience with up-to-date software engineering practices including object-oriented design, design patterns, testing, and secure coding principles

- Experience working with Azure Databricks, Spark, and modern data platforms supporting AI workloads

- Strong understanding of data pipelines, feature engineering, and data preparation for AI applications

- Experience with Azure cloud services supporting AI workloads

- Experience with Docker, Kubernetes, and cloud-native application deployment

- Familiarity with MLOps and LLMOps practices including model lifecycle management, monitoring, and continuous deployment

- Minimum 8+ years of hands-on experience in Software Engineering, Full Stack Development, Platform Engineering, Data Engineering, or related technical fields

- Minimum 3+ years of experience designing, developing, or deploying AI, Machine Learning, or Generative AI solutions

📌 Senior AI Engineer (Pune)
🏢 MyOmniCareer
📍 Pune