AI/ML Engineer

About this job

Job Description: AI/ML Engineer

• Experience: 2–3 Years
• Employment Type: Full-Time
• Department: Engineering / Artificial Intelligence & Machine Learning

About the Role

We are looking for a talented and motivated AI/ML Engineer with 2–3 years of hands-on experience in Python development, Generative AI, Large Language Models (LLMs), and machine learning.

The ideal candidate will have practical experience building Retrieval-Augmented Generation (RAG) pipelines, developing Model Context Protocol (MCP) servers and tools, implementing data engineering workflows, and deploying scalable AI/ML solutions in production environments.

You will work on developing intelligent applications, integrating LLMs with enterprise APIs and data sources, and building reliable, scalable AI-powered systems.

Key Responsibilities

• Design, develop, and maintain RAG pipelines, including document chunking, embeddings, vector search, and re-ranking.
• Build MCP (Model Context Protocol) servers and tools to connect internal APIs, services, and data sources with LLM-powered agents.
• Design, develop, and schedule DAG-based workflows using Databricks Workflows and/or Apache Airflow.
• Build and maintain scalable ETL and machine learning pipelines using PySpark, Delta Lake, and MLflow.
• Develop production-ready Python APIs and backend services using FastAPI or Django.
• Write unit tests, integration tests, and maintain high-quality, reusable, and maintainable code.
• Implement LLM evaluation frameworks, guardrails, and monitoring for model performance, cost, and latency.
• Collaborate with cross-functional teams to integrate AI/ML solutions into existing business applications.
• Troubleshoot, optimize, and continuously improve the performance, scalability, and reliability of AI/ML applications.

Required Technical Skills

1. Programming & Backend Development

• Strong proficiency in Python with at least 2 years of production-level development experience.
• Experience building REST APIs using FastAPI or Django.
• Knowledge of software engineering best practices, testing, and debugging.

2. Artificial Intelligence & Machine Learning

• Strong understanding of AI/ML fundamentals.
• Hands-on experience with scikit-learn, PyTorch, or TensorFlow.
• Practical knowledge of Large Language Models (LLMs) and Generative AI applications.

3. RAG & LLM Frameworks

• Experience developing RAG-based applications.
• Familiarity with LangChain, LlamaIndex, or LangGraph.
• Understanding of embeddings, vector databases, semantic search, chunking strategies, and re-ranking techniques.

4. Model Context Protocol (MCP)

• Understanding and hands-on experience with MCP.
• Ability to build MCP servers and tools for integrating APIs and external services with LLM agents.

5. Data Engineering & Databricks

• Hands-on experience with Databricks, PySpark, and Delta Lake.
• Experience building ETL and ML pipelines.
• Familiarity with MLflow for machine learning lifecycle management.

6. Workflow Orchestration

• Experience designing and managing DAG-based workflows.
• Hands-on experience with Databricks Workflows or Apache Airflow.

7. Databases & Cloud Technologies

• Strong SQL knowledge and experience with PostgreSQL.
• Familiarity with vector databases such as pgvector, FAISS, Qdrant, or similar technologies.
• Experience with AWS cloud services.

8. Development & Deployment Tools

• Proficiency with Git and version control.
• Experience with Docker and containerized applications.
• Understanding of REST API integration and deployment practices.

Good to Have

• Experience building AI agents and agentic workflows using LangGraph.
• Familiarity with RAG evaluation frameworks such as RAGAS and LangSmith.
• Knowledge of recommendation systems.
• Experience implementing CI/CD pipelines using GitHub Actions.
• Understanding of LLM observability, prompt optimization, and production monitoring.

Educational Qualifications

• B.Tech / B.E.…