Job Description :

We are looking for an experienced AI Engineer / Lead with hands-on expertise in Generative AI and Agentic AI to design, develop, and deploy production-grade, enterprise-scale AI solutions.

The ideal candidate should have strong proficiency in Python, Machine Learning, and multi-agent system orchestration, with proven experience delivering end-to-end implementations with minimal supervision.

Key Responsibilities :

- Design, build, and orchestrate multi-agent systems capable of autonomous decision-making and task execution.

- Lead the development and deployment of Generative AI solutions using LLMs and fine-tuned models.

- Implement RAG (Retrieval-Augmented Generation) pipelines with robust document parsing, re-ranking, and context optimization.

- Integrate AI agents into enterprise systems through APIs, function calling, and workflow orchestration frameworks (e.g., LangGraph, CrewAI, LlamaIndex, Haystack).

- Fine-tune and evaluate LLMs (using LoRA, PEFT, or QLoRA) for domain-specific use cases.

- Collaborate cross-functionally with data, platform, and DevOps teams to ensure scalable and secure AI deployments.

- Ensure production-grade quality performance optimization, monitoring, and continuous improvement.

- Provide technical mentorship to junior engineers (minimal team handling required).

Required Skills & Experience :

- 5 -8 years of total experience, with Min 3+ years in Generative AI and 1+ years Agentic AI with Min 2 or 3 Production grade implementation at Enterprise Level.

- Strong background in Machine Learning, Deep Learning, and Python programming.

- Hands-on experience with LLM frameworks (LangChain, LlamaIndex, Haystack, Semantic Kernel, etc.).

- Proficiency in multi-agent orchestration (CrewAI, LangGraph, Swarm, Autogen, or custom frameworks).

- Expertise in vector databases (FAISS, Pinecone, Chroma, Weaviate, etc.) and embedding models.

- Proven fine-tuning experience using LoRA, QLoRA, or PEFT.

- Experience in enterprise-grade GenAI implementations from PoC to production.

- Strong understanding of RAG architecture, document chunking, context optimization, and model evaluation.

- Familiarity with cloud platforms (AWS, Azure, GCP) and containerization (Docker, Kubernetes).

- Excellent problem-solving and debugging skills.