Join a dynamic team as an Agentic AI Engineer to develop, optimize, and deploy cutting-edge AI solutions, using advanced frameworks and MLOps practices.

About the Company

Shree HR Services is a dedicated human resource consulting firm that specializes in strategic hiring for both IT and non-IT sectors. Our mission is to connect talented professionals with leading organizations, ensuring the best match for career growth and company success. With a commitment to client satisfaction and an extensive network, we are a trusted partner in the recruitment landscape.

Role Overview

As an Agentic AI Engineer, you will play a pivotal role in driving our AI capabilities forward. This position is designed for a hands-on professional who is passionate about developing, optimizing, and deploying AI solutions. The successful candidate will engage in every aspect of the AI project lifecycle, from innovation to implementation, ensuring our systems are scalable and functional. Collaboration with architects and data scientists will be crucial in translating architectural blueprints into real-world applications.

Key Responsibilities

• Agentic Development:

  • Build LLM-based applications and multi-step workflows using frameworks like Microsoft Agent Framework, AutoGen, and LangChain.
  • Implement Retrieval-Augmented Generation pipelines inclusive of chunking, embedding, and vector search.
  • Design agent capabilities with memory, and human-in-the-loop checkpoints.
  • Fine-tune and optimize models for specific domain tasks to enhance performance.

• Integration & Delivery:

  • Develop and expose AI functionalities via FastAPI endpoints and manage integrations with APIs.
  • Handle vector databases to facilitate data retrieval effectively.

• MLOps & Productionization:

  • Use Docker and Kubernetes for deploying AI models on AWS/Azure while ensuring high availability and performance.
  • Implement observability solutions for tracking system performance and output reliability.
  • Execute CI/CD for ML, ensuring comprehensive testing processes.

• Collaboration:

  • Liaise with senior architects and project managers to align technical efforts with business needs, ensuring efficient project delivery.
  • Promote code quality through peer reviews and maintain a repository of reusable AI components.

Tech Stack

• Programming Languages: Python
• Frameworks: LangChain, LangGraph, AutoGen, LlamaIndex
• Deployment Tools: Docker, Kubernetes
• Cloud Platforms: AWS, Azure
• MLOps Tools: MLflow, DVC
• Databases: Pinecone, Qdrant, pgvector
• Other Tools: FastAPI, LangSmith, Arize Phoenix, G-Eval, TruLens

Qualifications

• Experience: Minimum 4+ years in software engineering, data engineering, or machine learning; at least 1 year in building LLM/Gen AI applications.
• Python Skills: Strong expertise in Python, including OOP, async programming, packaging, and testing.
• LLM Frameworks: Hands-on experience with at least one framework such as LangChain, LangGraph, CrewAI, AutoGen, or LlamaIndex.
• Gen AI Knowledge: Familiarity with LLM APIs (like OpenAI, Anthropic Claude, Gemini) and prompt design techniques.
• Cloud Basics: Understanding of AWS or Azure, comfortable with REST APIs and Git workflows.
• MLOps Experience: Proven track record in deploying, monitoring, and maintaining AI systems in production, specifically with Docker, Kubernetes, CI/CD pipelines, and observability tools.
• Educational Background: B.Tech / B.E. / M.Sc. in Computer Science, Information Technology, or related fields.

Good to Have:

• Exposure to evaluation tools like G-Eval, RAGAS, TruLens, or LangSmith for assessing LLM output quality.
• Basic experience with MLflow or DVC for experiment tracking.
• Experience with Pydantic-based output parsing and function/tool calling techniques.

• Competitive salary
• Hybrid work model (remote and office)
• Opportunities for continuous learning and professional growth
• Flexible work hours
• Health and wellness benefits
• Collaborative work environment with a focus on innovation