Chief Engineer - Artificial Intelligence

Chief Engineer - Artificial Intelligence

AI Architecture | Production Engineering | LLM, RAG & Agentic AI

Primary objective: Build secure, scalable and reusable AI capabilities that move from experimentation to reliable production use across DocTutorials products and business functions.

Department

Technology & Product Engineering

Location

Hyderabad / Chennai

Reports to

Vice President - Technology

Experience

10+ years in software engineering, including 5+ years in AI/ML

Role Summary

The Chief Engineer - AI will define and lead AI engineering architecture, standards and production implementation. This is a senior, hands-on technical leadership role responsible for building reliable AI platforms and guiding AI engineers, data teams and application teams.

Key Responsibilities

AI Strategy and Architecture

• Define the AI engineering strategy, architecture and technical roadmap.
• Evaluate and select suitable models, frameworks, vector databases and AI platforms.
• Make practical build-versus-buy and open-source-versus-commercial decisions.
• Ensure AI solutions are modular, reusable, scalable, secure and cost-effective.

Production AI Engineering

• Lead AI initiatives from use-case assessment and proof of concept through production deployment.
• Build reusable AI services, APIs, pipelines and platform components for web, mobile and internal applications.
• Establish development, testing, deployment, monitoring and production-support practices.
• Resolve complex issues involving model quality, retrieval, performance, reliability and cost.

LLM, RAG and Agentic AI

• Design LLM applications, enterprise RAG solutions and controlled AI-agent workflows.
• Build document processing, chunking, embedding, indexing, retrieval and response pipelines.
• Implement source traceability, human approval and clear permissions for sensitive use cases.
• Improve response quality through prompt design, retrieval optimisation and evaluation.

AI Quality, Security and Responsible AI

• Define evaluation standards for accuracy, relevance, groundedness, safety, latency and cost.
• Introduce benchmark datasets and regression testing for prompts, models and retrieval pipelines.
• Implement safeguards for hallucinations, unsupported responses, data leakage and unsafe actions.
• Ensure role-based access, encryption, audit logging, secure secrets handling and approved data usage.

AI Platform and Integration

• Create common AI capabilities and integration standards that can be reused across products and teams.
• Integrate AI services with applications, databases and approved enterprise data sources.
• Implement observability for model usage, quality, errors, response time and cost.
• Reduce dependency on a single model provider, individual engineer or external vendor.

Technical Leadership and Team Development

• Define AI engineering standards for architecture, coding, review, testing and documentation.
• Remain hands-on through design reviews, critical code reviews, debugging and focused prototypes.
• Mentor AI/ML engineers, data engineers and application teams; support hiring and capability building.
• Work with Product and business teams to convert high-value problems into measurable AI solutions.

Required Skills and Experience

• 10+ years of software engineering experience, including 5+ years in practical AI/ML engineering.
• Proven experience moving AI solutions from prototype to reliable production use.
• Strong Python and production API development experience, preferably FastAPI.
• Strong knowledge of LLMs, RAG, prompt engineering, embeddings and agentic AI.
• Experience with vector databases such as pgvector, Qdrant, Milvus or Weaviate.
• Experience with LangChain, LlamaIndex, Haystack or similar orchestration frameworks.
• Knowledge of cloud architecture (preferably AWS), microservices, databases, queues and distributed systems.
• Experience with Docker, Kubernetes, CI/CD, observability and production support.
• Strong understanding of application security, data privacy and responsible-AI engineering.
• Demonstrated technical leadership, mentoring and stakeholder-management capability.

Good-to-Have Experience

• Healthcare, medical education, EdTech or digital-learning platforms.
• Medical-content intelligence, knowledge graphs, ontologies, taxonomy or semantic search.
• Clinical Case Library, personalised learning or recommendation systems.
• Multi-modal AI involving text, audio, images or video.
• Healthcare-data privacy, de-identification or standards such as SNOMED CT, ICD, HL7 or FHIR.

How Success Will Be Measured

• Production adoption and measurable business or learner impact of AI capabilities.
• Accuracy, groundedness, reliability, security and cost efficiency of AI solutions.
• Reusable AI services delivered across products with reduced technical and vendor dependency.
• Improved capability, engineering quality and ownership within the AI team.

We are looking for a hands-on AI engineering leader who can distinguish a valuable production capability from an attractive demo and build AI that is secure, scalable, measurable and maintainable.