Senior Generative AI Engineer

We are looking for a Senior Generative AI Engineer with 8+ years of experience in designing and developing AI/ML solutions using large language models (LLMs), NLP, and cloud-based AI platforms. The ideal candidate should have strong expertise in Python, GenAI frameworks, scalable API development, and document intelligence solutions. The candidate should also have experience building traceable, explainable, and auditable AI systems. Experience in the US healthcare domain is a plus.
Responsibilities:
Design and develop GenAI applications using LLMs such as GPT, Claude, Gemini, or open-source models.
Build AI/NLP pipelines for document extraction, summarisation, classification, and structured JSON generation.
Develop Retrieval-Augmented Generation (RAG) applications using vector databases and semantic search.
Create scalable REST APIs and microservices for AI-powered workflows.
Optimise prompts, context management, and hallucination reduction techniques.
Design and implement OCR and document intelligence pipelines for large-scale document processing.
Fine-tune and evaluate LLMs for domain-specific use cases.
Implement AI evaluation frameworks to measure accuracy, relevance, latency, and cost.
Build explainable, traceable, and auditable AI systems with logging and versioning.
Integrate AI services with enterprise applications and business workflows.
Collaborate with data scientists, product managers, QA, and engineering teams to deliver production-ready solutions.
Monitor, troubleshoot, and optimise AI applications for performance and scalability.
Implement security, governance, and responsible AI best practices.
Mentor junior engineers and participate in architecture and design discussions.
Stay updated with the latest advancements in generative AI, LLMs, and AI infrastructure.
Requirements:
8+ years of software development experience.
Strong programming expertise in Python.
Expertise in building traceable, explainable, and auditable AI solutions.
Familiarity with Agile/Scrum development methodologies.
Strong understanding of software design principles and system architecture.
Experience with API design, integration, and deployment.
Hands-on experience with OpenAI/Azure OpenAI, LangChain, LlamaIndex, or Semantic Kernel; prompt engineering and NLP; Retrieval-Augmented Generation (RAG); vector databases (Pinecone, FAISS, ChromaDB, Weaviate, Azure AI Search); embeddings and semantic search; JSON schema-based information extraction; REST APIs and microservices; FastAPI or Flask; OCR frameworks (Azure Document Intelligence, Tesseract, Google Document AI); and AI evaluation and prompt testing frameworks.
Cloud and Infrastructure: Microsoft Azure (Preferred), Azure AI Services, Azure Machine Learning, Azure Functions, Azure Kubernetes Service (AKS), Azure AI Search, Docker, Kubernetes, Git, CI/CD pipelines (Azure DevOps/GitHub Actions), SQL and NoSQL databases, Redis and message queues (preferred).
Good to Have:
Experience in the US healthcare domain.
Knowledge of ICD-10 HCC and risk adjustment.
Experience with EMR/EHR systems.
Clinical NLP experience.
Healthcare document processing solutions.
FHIR and HL7 standards.
OCR pipelines and healthcare AI solutions.
Experience with HIPAA-compliant AI applications.
Exposure to MLOps, LLMOps, and AI governance frameworks.
Knowledge of model monitoring and observability tools.
Preferred Qualifications:
A bachelor's or master's degree in computer science, AI/ML, data science, or a related field.
Experience building enterprise-scale AI platforms.
Strong problem-solving and analytical skills.
Excellent communication and stakeholder management skills.
Experience leading technical design discussions and mentoring engineering teams.
Ability to work in a fast-paced, collaborative environment.
Passion for continuous learning and adopting emerging AI technologies.
Experience delivering production-grade AI applications with measurable business impact.

Experience
8-12 yrs