Generative AI Engineering Lead

Job Description:

We are seeking a highly skilled and hands-on GenAI Engineering Lead to architect, develop, and scale enterprise-grade Generative AI solutions leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and cloud-native AI platforms.

The ideal candidate will have strong expertise in AI application development, machine learning engineering, distributed systems, and cloud technologies, with a proven track record of delivering production-ready AI solutions.

As a GenAI Engineering Lead, you will drive the design and implementation of intelligent applications, lead technical decision-making, mentor engineering teams, and collaborate closely with Product, Data Science, Security, and Business stakeholders to deliver impactful AI-powered solutions.

Key Responsibilities:

- Design, develop, and deploy enterprise-scale Generative AI applications using state-of-the-art LLMs.

- Build intelligent conversational AI systems, virtual assistants, knowledge management platforms, document intelligence solutions, and AI-powered automation tools.

- Develop scalable AI architectures that support high availability, reliability, and performance.

- Architect and implement end-to-end RAG pipelines for enterprise knowledge retrieval and contextual AI responses.

- Design document ingestion, chunking, embedding generation, indexing, and retrieval strategies.

- Optimize retrieval quality using hybrid search, semantic search, reranking, and metadata filtering techniques.

- Integrate vector databases and search platforms for efficient information retrieval.

- Design and implement autonomous and multi-agent workflows using modern agent frameworks.

- Build AI agents capable of reasoning, planning, tool utilization, memory management, and workflow orchestration.

- Integrate external APIs, enterprise applications, databases, and business systems into agent ecosystems.

- Develop agent monitoring, observability, and evaluation frameworks.

- Fine-tune, customize, and optimize foundation models for domain-specific use cases.

- Develop prompt engineering and prompt optimization strategies to improve model performance.

- Evaluate model outputs using quantitative and qualitative metrics.

- Work with open-source and commercial LLMs including GPT, Claude, Llama, Mistral, Gemini, and similar models.

- Build cloud-native AI platforms on AWS, Azure, or GCP.

- Deploy AI services using containerized and microservices-based architectures.

- Design scalable inference and serving infrastructure for LLM applications.

- Implement CI/CD pipelines and MLOps practices for AI deployments.

- Lead technical architecture discussions and provide guidance to engineering teams.

- Mentor developers and AI engineers on GenAI best practices.

- Collaborate with Product Managers, Data Scientists, Security Teams, and Business Stakeholders to define AI roadmaps.

- Participate in solution design, effort estimation, and technical planning.

- Implement AI governance, model monitoring, and compliance frameworks.

- Ensure responsible AI practices including fairness, explainability, privacy, and security.

- Develop guardrails to mitigate hallucinations, prompt injection, data leakage, and security vulnerabilities.

- Monitor model performance and continuously improve AI solution quality.

Required Technical Skills:

1. Programming & Development:

- Strong expertise in Python

- Experience with REST APIs and backend frameworks such as FastAPI

- Strong understanding of software engineering principles and design patterns

2. Generative AI Frameworks:

- Hands-on experience with:

1. LangChain

2. LlamaIndex

3. Semantic Kernel (preferred)

4. AutoGen (preferred)

5. CrewAI (preferred)

3. LLM Platforms:

- OpenAI API

- Azure OpenAI Service

- Anthropic Claude APIs

- Google Gemini APIs

- Hugging Face ecosystem

4. RAG & Search Technologies:

- Retrieval-Augmented Generation (RAG)

- Embedding models

- Semantic Search

- Hybrid Search

- Reranking Frameworks

- Vector Databases

1. Pinecone

2. Weaviate

3. ChromaDB

4. FAISS

5. Milvus (preferred)

5. Cloud Platforms:

- AWS

- Microsoft Azure

- Google Cloud Platform (GCP)

6. Containers & Orchestration:

- Docker

- Kubernetes

- Helm (preferred)

7. Data & Databases:

- PostgreSQL

- MongoDB

- Elasticsearch/OpenSearch

- Redis

8. DevOps & MLOps:

- CI/CD Pipelines

- GitHub Actions

- Jenkins

- MLflow

- Model Monitoring Tools

Qualifications:

- 915 years of overall software engineering experience.

- 3+ years of hands-on experience building production-grade GenAI applications.

- Strong experience in designing and implementing RAG architectures.

- Experience deploying LLM applications in cloud environments.

- Proven experience working with vector databases and embedding models.

- Experience leading technical teams and enterprise-scale projects.

- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or related field.

- Experience with fine-tuning LLMs using LoRA, QLoRA, PEFT, or similar techniques.

- Knowledge of GPU infrastructure and model optimization techniques.

- Experience with multi-agent systems and autonomous workflows.

- Familiarity with AI evaluation frameworks and benchmarking methodologies.

- Contributions to AI open-source projects or research publications are a plus.