Coforge - GenAI Technical Lead - LLM/RAG

Role & Responsibilities : The Gen AI Tech Lead will be responsible for leading the design, development, deployment, and optimization of enterprise-grade Generative AI solutions. The role involves architecting scalable AI applications, mentoring engineering teams, collaborating with business stakeholders, and driving the adoption of Large Language Models (LLMs), RAG pipelines, AI agents, and cloud-native AI platforms.Technical Skills & Expertise : 1. Generative AI & LLMs : - Hands-on experience with OpenAI, Azure OpenAI, Claude, Gemini, Llama, Mistral, Hugging Face- Prompt Engineering- Retrieval-Augmented Generation (RAG)- AI Agents & Agentic AI Frameworks- LangChain- LangGraph- LlamaIndex- Semantic Search- Function Calling & Tool Integration2. LLMOps & MLOps : - MLflow- Kubeflow- Airflow- SageMaker- Azure ML- Vertex AI- Model Versioning & Deployment- Model Monitoring- Continual Learning- A/B Testing3. Vector Databases : - Pinecone- Weaviate- ChromaDB- Qdrant- FAISS4. Cloud Platforms : - Microsoft Azure- Google Cloud Platform (GCP)- Amazon Web Services (AWS)- Azure AI Services- Vertex AI- SageMaker5. Programming : - Python- Scikit-learn- TensorFlow- PyTorch- REST APIs6. DevOps & Platforms : - Docker- Kubernetes- CI/CD Pipelines- Git- Terraform (Preferred)7. Monitoring & Observability : - Prometheus- Grafana- ELK Stack- Datadog8. Architecture & Governance : - Enterprise AI Architecture- AI Governance- Security & Responsible AI- Scalability & Performance Optimization- Cloud-Native AI DeploymentsPreferred Candidate Profile : 1. Generative AI Solution Architecture : - Lead the design and implementation of enterprise-scale Generative AI solutions.- Architect AI-powered applications using LLMs, RAG pipelines, AI agents, and conversational AI frameworks.- Define LLM selection strategies, prompt engineering best practices, and orchestration workflows.- Design scalable AI architectures that ensure performance, security, and cost optimization.2. LLMOps & MLOps Leadership : - Design and implement end-to-end ML/LLM pipelines with automation for training, deployment, monitoring, and retraining.- Lead model lifecycle management using MLflow, Kubeflow, Airflow, Azure ML, SageMaker, and Vertex AI.- Drive continual learning, model versioning, experimentation, and A/B testing strategies.- Establish best practices for production-grade AI deployments.3. Cloud & Platform Engineering : - Architect cloud-native AI solutions across Azure, GCP, and AWS.- Design scalable containerized deployments using Docker and Kubernetes.- Implement Infrastructure as Code and CI/CD pipelines for AI workloads.- Optimize cloud infrastructure for performance, scalability, and cost efficiency.4. Vector Database & RAG Implementation : - Design and implement Retrieval-Augmented Generation (RAG) architectures.- Build embedding pipelines and semantic search solutions.- Optimize vector databases including Pinecone, Weaviate, ChromaDB, Qdrant, and FAISS.- Implement document ingestion, indexing, retrieval, and contextual response generation.5. Performance Optimization & Monitoring : - Implement monitoring and observability for AI applications using Prometheus, Grafana, ELK Stack, and Datadog.- Optimize GPU utilization, inference latency, throughput, and model serving performance.- Ensure high availability, resilience, and scalability of AI platforms.6. Leadership, Mentoring & Collaboration : - Provide technical leadership and architectural guidance to AI engineering teams.- Mentor engineers on Generative AI, LLMOps, and cloud-native AI best practices.- Collaborate with Data Scientists, Product Managers, Solution Architects, and Business Stakeholders.- Review solution designs, conduct architecture reviews, and drive technical decision-making.- Support client discussions, solution proposals, estimations, and proof-of-concepts where required.Nice to Have : - Experience with Multi-Agent AI Systems.- Exposure to MCP (Model Context Protocol).- Knowledge of AI Guardrails and Responsible AI frameworks.- Experience with GraphRAG and Knowledge Graphs.- Familiarity with NVIDIA NIM, vLLM, or Ollama.- Azure AI Engineer Associate, Google Professional Machine Learning Engineer, or AWS Machine Learning Specialty Certification. (ref:hirist.tech)