Job Description – Lead AI Engineer

Job Title: Lead AI Engineer

About the Role

We are looking for an experienced Lead AI Engineer (EL4) to lead the architecture, development, and deployment of enterprise-grade Generative AI and Agentic AI solutions. The ideal candidate will have deep expertise in RAG architecture, LLM-based applications, AI platform architecture, LLMOps, vector search, semantic retrieval, and enterprise AI integration.

The role requires strong hands-on experience with Python, LangChain, LangGraph, Semantic Kernel, LlamaIndex, AutoGen, CrewAI, and cloud AI platforms including Azure OpenAI, Azure AI Foundry, AWS Bedrock, and Vertex AI.

The candidate will be responsible for building scalable, secure, governed, and production-ready AI solutions, particularly for Healthcare and Insurance use cases.

Key Responsibilities

- Lead the architecture and development of Generative AI and Agentic AI solutions for enterprise applications.
- Design scalable RAG architectures combining LLMs, embeddings, vector databases, knowledge graphs, and enterprise data sources.
- Develop advanced LLM-based applications, AI agents, copilots, conversational systems, and intelligent automation solutions.
- Design AI Platform Architecture covering model integration, orchestration, retrieval, security, monitoring, governance, and deployment.
- Build multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, and Semantic Kernel.
- Develop RAG and AI applications using LangChain and LlamaIndex.
- Implement semantic retrieval, vector search, hybrid search, and knowledge graph-based retrieval.
- Design and optimize embedding pipelines, chunking strategies, metadata enrichment, indexing, and retrieval mechanisms.
- Work with Azure OpenAI, Azure AI Foundry, AWS Bedrock, Vertex AI, OpenAI, and Anthropic models and services.
- Lead LLMOps practices including evaluation, monitoring, prompt/version management, model lifecycle management, observability, and production optimization.
- Develop AI applications using Python and modern AI/ML frameworks.
- Integrate enterprise applications, APIs, databases, document repositories, and business workflows with AI platforms.
- Establish AI Governance and Responsible AI practices covering security, privacy, explainability, transparency, model risk, and compliance.
- Design mechanisms to reduce hallucinations and improve groundedness, relevance, accuracy, and response quality.
- Evaluate and optimize LLM performance, latency, scalability, token consumption, and infrastructure costs.
- Lead technical discussions, architecture reviews, proof-of-concepts, and AI modernization initiatives.




- Mentor AI/ML engineers and establish engineering standards and best practices.
- Collaborate with product managers, enterprise architects, data engineers, security teams, and business stakeholders.
- Ensure AI solutions comply with enterprise security, governance, and regulatory requirements.

Required Technical SkillsGenerative AI & LLMs

- Strong hands-on experience with Generative AI and LLM-based solutions.
- Deep understanding of Transformer architectures, LLMs, embeddings, prompt engineering, context management, and model evaluation.
- Experience with OpenAI, Anthropic, and other foundation models.
- Strong understanding of LLM limitations, hallucination mitigation, grounding, and responsible AI.

Agentic AI

- Strong experience designing and implementing Agentic AI architectures.
- Experience with multi-agent orchestration and tool/function calling.
- Hands-on experience with one or more of:
- LangGraph
- LangChain
- Semantic Kernel
- LlamaIndex
- AutoGen
- CrewAI

RAG & Retrieval

- Strong expertise in RAG Architecture and enterprise retrieval systems.
- Experience with:
- Vector Search
- Semantic Retrieval
- Hybrid Search
- Embeddings
- Knowledge Graphs
- Metadata filtering
- Re-ranking
- Document chunking and indexing
- Experience with Chroma DB, Azure AI Search, or equivalent vector/search technologies.

Cloud AI Platforms

Strong experience with one or more of the following:

- Azure OpenAI
- Azure AI Foundry
- AWS Bedrock
- Google Vertex AI
- OpenAI APIs
- Anthropic APIs

Multi-cloud AI experience is highly desirable.

AI Application Development

- Strong Python programming skills.
- Experience developing production-grade AI applications and APIs.
- Knowledge of REST APIs, microservices, event-driven architectures, and enterprise integration patterns.
- Experience integrating LLMs with enterprise applications, databases, knowledge repositories, and business workflows.

LLMOps & AI Platform Engineering

- Experience implementing LLMOps/MLOps practices.
- Model and prompt versioning.
- LLM evaluation and benchmarking.
- AI observability and monitoring.
- Production deployment and scaling.
- Cost and latency optimization.
- Automated testing and evaluation of AI applications.

AI Governance & Responsible AI

- Strong understanding of Responsible AI principles.




- Experience implementing:
- AI governance
- Data privacy and security
- Access controls
- Prompt and response safety
- PII protection
- Auditability
- Explainability
- Model risk management
- Ability to design enterprise AI solutions aligned with organizational governance and compliance requirements.

Healthcare / Insurance Domain

- Experience working on Healthcare, Insurance, Life Sciences, or other highly regulated domains is strongly preferred.
- Understanding of sensitive enterprise data, privacy, regulatory compliance, and governance requirements.
- Experience building AI solutions for use cases such as:
- Healthcare knowledge assistants
- Claims processing
- Policy/document intelligence
- Medical/insurance document summarization
- Customer/agent copilots
- Enterprise search
- Underwriting support
- Intelligent workflow automation

Key Leadership Responsibilities – EL4

- Own technical architecture and delivery of complex Enterprise AI initiatives.
- Define AI engineering standards, reusable frameworks, and reference architectures.
- Make technology decisions across LLMs, agent frameworks, retrieval architectures, cloud AI platforms, and AI infrastructure.
- Conduct architecture and code reviews.
- Mentor senior engineers and technical teams.
- Drive AI POCs from concept through productionization.
- Partner with business and technology leadership to identify high-value AI opportunities.
- Establish best practices for RAG, Agentic AI, LLMOps, AI governance, and Responsible AI.
- Lead troubleshooting and resolution of complex production AI issues.

Good to Have

- Experience with Kubernetes, Docker, CI/CD, Terraform, or cloud-native architectures.
- Experience with MLflow or other model lifecycle platforms.
- Knowledge of Graph databases such as Neo4j.
- Experience with advanced RAG techniques such as query transformation, contextual retrieval, re-ranking, and agentic RAG.
- Experience with fine-tuning, LoRA/PEFT, or model adaptation.
- Knowledge of evaluation frameworks such as RAGAS, DeepEval, or equivalent.
- Experience building enterprise AI Centers of Excellence or AI platforms.

Key Competencies

- Robust AI architecture and system-design skills.
- Excellent problem-solving and analytical abilities.
- Strong understanding of enterprise software architecture.
- Ability to translate business problems into scalable AI solutions.
- Strong technical leadership and stakeholder-management skills.
- Excellent communication and mentoring abilities.
- Strong focus on security, governance, scalability, reliability, and responsible AI.

Work Location: Remote

📌 Lead AI Engineer (India)
🏢 WebSenor InfoTech
📍 India