An esteem client of Innoquest Consulting , into AI into the healthcare domain is seeking AI engineer for the office in Pune

Role : Senior AI Engineer

About the Role

We are looking for an experienced Senior AI Engineer to design, build, and deploy production grade AI and Generative AI solutions that power our products.

The ideal candidate will have a strong foundation in machine learning and software engineering, practical experience building applications using Large Language Models (LLMs), and hands-on expertise with the Microsoft Azure technology stack.

You will work across the full AI development lifecycle, from data preparation, experimentation, and model integration to application development, deployment, monitoring, and continuous improvement. You will collaborate closely with product, engineering, data, and platform teams to translate business requirements into scalable AI solutions.

Key Responsibilities

• Design, develop, and deploy AI and Generative AI applications for real world business problems.
• Build applications using Large Language Models (LLMs), including prompt engineering, structured outputs, function and tool calling, agents, and multi step AI workflows.
• Design and implement Retrieval Augmented Generation (RAG) pipelines using embeddings, vector databases, document processing, retrieval, and reranking techniques.
• Integrate foundation models and LLM APIs such as Azure OpenAI into enterprise applications.
• Understand and apply core LLM concepts including Transformers, tokenization, embeddings, context windows, attention, inference, fine tuning, and model evaluation.
• Develop scalable APIs, backend services, and AI workflows for integrating AI capabilities into existing products.
• Build and maintain data pipelines for AI and ML training, evaluation, retrieval, and inference.
• Evaluate LLM and GenAI applications for accuracy, hallucination, relevance, latency, reliability, safety, and cost.
• Implement AI application monitoring, observability, versioning, testing, and CI/CD practices.
• Design and deploy AI solutions using the Microsoft Azure ecosystem, including Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Machine Learning, compute, storage, container, security, and DevOps services.
• Work with traditional machine learning and deep learning models where required.
• Conduct experiments, error analysis, and performance optimisation to continuously improve AI systems.
• Collaborate with product managers and engineers to convert business requirements and use cases into scalable AI solutions.
• Write clean, modular, well tested, production grade Python code and participate in architecture, design, and code reviews.
• Mentor junior engineers and contribute to AI and ML engineering standards and best practices across the organisation.

Required Skills & Experience

• 6 to 10 years of software engineering, machine learning, data science, or AI engineering experience, with experience building and deploying production applications.
• Strong programming skills in Python, with a good understanding of data structures, algorithms, APIs, object oriented programming, and software engineering fundamentals.
• Hands on experience developing applications using Generative AI and Large Language Models.
• Working knowledge of how LLMs operate, including Transformers, tokens, embeddings, context windows, attention mechanisms, inference, and fine tuning concepts.
• Practical experience with prompt engineering, RAG, embeddings, vector search, and LLM evaluation.
• Experience integrating LLM APIs such as Azure OpenAI or OpenAI into production applications.
• Strong hands on experience building and deploying applications on Microsoft Azure.
• Strong understanding of REST APIs, microservices, and backend application development.
• Experience with containerisation using Docker and exposure to Kubernetes and AKS.
• Experience with ML and DL frameworks such as PyTorch, TensorFlow, or scikit learn.
• Solid foundation in machine learning concepts including regression, classification, tree based models, clustering, deep learning, and Transformers.
• Experience working with Pandas, NumPy, SQL, and data processing frameworks such as Spark.
• Familiarity with Databricks, including Spark on Databricks, Delta Lake, and MLflow.
• Familiarity with MLOps and LLMOps concepts including experiment tracking, model and prompt versioning, automated evaluation, CI/CD, monitoring, and deployment.
• Strong problem solving and debugging skills.
• Strong communication skills and the ability to explain AI concepts and technical tradeoffs to technical and non technical stakeholders.

Good to Have

• Experience building enterprise RAG systems and working with vector databases and vector search platforms.
• Experience with AI agents, tool and function calling, multi agent systems, or agentic workflows.
• Experience with frameworks such as LangChain, LangGraph, Semantic Kernel, LlamaIndex, or similar GenAI frameworks.
• Experience implementing guardrails, responsible AI practices, prompt security, PII protection, and secure LLM application architectures.
• Experience with LLM evaluation frameworks and techniques for measuring groundedness, relevance, hallucination, and retrieval quality.
• Experience with fine tuning, LoRA, PEFT, quantisation, distillation, or optimisation of foundation models.
• Understanding of different model families, including proprietary and open source LLMs.
• Experience working with NLP, computer vision, recommendation systems, or multimodal AI applications.
• Experience designing highly available and cost efficient AI applications at scale.
• Contributions to open source AI projects, publications, patents, or relevant technical communities.

Education

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Engineering, Mathematics, or a related field, or equivalent practical experience.