Role Title: AI/ML – Python Engineer | Engineering as a Service/ Operate

Location: Pune & Chennai

Entity: Deloitte Touche Tohmatsu India LLP

We are looking for an AI/ML Engineer with 4 to 6 years of hands-on experience in AI/ML engineering and software development, with strong expertise in Generative AI, Large Language Models (LLMs), Python, RAG, and Agentic AI. The ideal candidate should have experience designing, developing, and deploying scalable AI solutions using modern AI/ML frameworks and cloud platforms.

Must Have: -

• Strong programming skills in Python with 4–6 years of software development experience.
• Hands-on experience with Generative AI and Large Language Models (LLMs) such as OpenAI, Gemini, Claude, Llama, or similar models.
• Experience designing and developing RAG (Retrieval-Augmented Generation) applications using embeddings, vector databases, and semantic search.
  Hands-on experience with LLM frameworks such as LangChain, LangGraph, LlamaIndex.
• Experience building Agentic AI applications, including tool/function calling, planning, memory, workflow orchestration, and multi-agent systems.
  Strong understanding of Prompt Engineering, embeddings, LLM evaluation, model optimization, and responsible AI practices.
• Experience developing and integrating REST APIs using frameworks such as FastAPI or Flask.
• Good understanding of SQL/RDBMS and NoSQL databases.
• Strong knowledge of Python programming, OOP, data structures, algorithms, exception handling, and software engineering best practices.
• Experience with Git/GitHub/GitLab and Agile software development practices.

Good-To-Have Skills: -

• Cloud platforms such as GCP, Azure, or AWS.
• Experience with Vertex AI, Azure OpenAI, AWS Bedrock, or similar managed AI/ML platforms.CI/CD pipelines, Jenkins, GitHub Actions, or Azure DevOps.Apache Kafka or other messaging/event-streaming technologies, Knowledge of LLM evaluation.
• Observability frameworks like RAGAS, DeepEval, LangSmith, or MLflow.Vector databases such as ChromaDB, FAISS, Pinecone, Weaviate, Milvus, or Vertex AI Vector Search.
• Experience with MLOps, model monitoring, model lifecycle management, and production deployment.
• Experience in Banking/BFSI domain or other enterprise domains is an added advantage.
  
  
  

Key Responsibilities: -

• Design, develop, and maintain scalable AI/ML and Generative AI applications.
  Build and optimize RAG pipelines, including document processing, chunking, embeddings, retrieval, re-ranking, and LLM-based response generation.
• Design & develop Agentic AI systems with tool calling, planning, memory, workflow orchestration, & multi-agent capabilities.
• Integrate LLM-based applications with enterprise APIs,DBs, messaging systems, & business apps.
• Develop scalable REST APIs and backend services for AI/ML applications.
• Implement effective prompt engineering, model evaluation, testing, & performance optimization.
• Evaluate AI solutions using appropriate quality, accuracy, relevance, latency, and reliability metrics.
• Write clean, maintainable, reusable, & testable Python code following software engineering practices.
• Troubleshoot, debug, and optimize AI applications for performance, scalability, security, and reliability.
• Participate in code reviews, technical design discussions, testing, debugging, & Agile/Scrum activities.
• Work closely with Data Scientists, Software Engineers, Cloud Engineers, QA teams, and business stakeholders to deliver high-quality AI solutions.
  Stay updated with the latest developments in Generative AI, LLMs, Agentic AI, RAG,
• AI/ML frameworks, and cloud AI technologies, and contribute to innovation and PoC initiatives.

Preferred Qualifications / Good to Have:

• BE/B.tech, ME/M.tech, BCA, MCA, BSC, MSC or relevant experience.