- Design and deploy end-to-end generative AI solutions — from data ingestion and RAG pipelines to model serving, agent orchestration, and prompt engineering — in production environments.
- Build and optimize Python-based backend services using LangChain, LlamaIndex, and agent frameworks (e.g., AutoGen, CrewAI) for enterprise use cases.
- Integrate LLMs (OpenAI, Anthropic, Mistral, Llama 3, etc.) with enterprise systems (CRM, ERP, Knowledge Bases) via API gateways and vector DBs (Pinecone, Weaviate, FAISS).
- Collaborate with data scientists to fine-tune, evaluate, and deploy open-source LLMs on cloud platforms (AWS, Azure, GCP) using SageMaker, Vertex AI, or Azure ML.
- Implement observability, cost monitoring, and guardrails (safety, hallucination detection, rate limiting) for GenAI deployments.
- Mentor junior engineers, document architecture decisions,



and enforce MLOps best practices (CI/CD, model versioning, drift detection).

Skills & Qualifications

- Must-Have
- Python
- LangChain
- LlamaIndex
- OpenAI API
- FAISS
- Pinecone
- Vector Databases
- LLM Fine-tuning
- RAG Architectures
- Agent Frameworks
- API Gateway Integration
- Cloud Platforms (AWS/Azure/GCP)
- Model Monitoring Tools
- CI/CD for ML

- Preferred
- AutoGen
- CrewAI
- MLflow

Benefits & Culture Highlights

- Work on bleeding-edge GenAI projects for global clients across healthcare, finance, and logistics.
- Flexible PTO, quarterly hackathons, and dedicated AI research time.
- Prospect to publish whitepapers, speak at AI conferences, and influence enterprise AI roadmaps.

📌 Gen AI Engineer_5+ years (Gurugram)
🏢 Zorba Consulting India
📍 Gurugram