Job Description :

You will lead the development of multi-agent AI systems and advanced generative AI solutions across our AI SAAS platform and client deployments.

Key Responsibilities :

- Design and develop production-grade multi-agent systems (planning, tools, memory, evaluation).

- Implement LLM architectures and fine-tuning (e.g., PEFT/LoRA) with alignment/safety practices.

- Architect advanced RAG end-to-end (using vector, SQL, or knowledge graph approaches).

- Build agent orchestration frameworks and prompt engineering tooling with tracing/observability.

- Develop semantic search and retrieval pipelines; maintain data freshness and evaluation loops.

- Collaborate with product and client teams to deliver solutions from design to deployment.

- Build and maintain cloud AI infrastructure with MLOps (CI/CD, registries, monitoring).

Required Skills & Qualifications (Must-have) :

- 3 - 4 years of professional experience building Generative AI applications with LLMs.

- Hands-on, production experience with multi-agent frameworks (e.g., Autogen, LangGraph, CrewAI, LangChain Agents).

- Expert Python and solid software architecture/testing practices.

- Strong data science foundation with pandas for analysis, feature prep, and evaluation.

- Proven delivery of advanced RAG (vector retrieval, SQL agents for grounded queries, and KG-based retrieval where appropriate).

- Experience with model fine-tuning and alignment techniques.

- Cloud experience (AWS/GCP/Azure), containerization (Docker), and orchestration (Kubernetes/Batch).

- Working knowledge of MLOps (model registries, CI/CD, offline/online evaluations, monitoring).

Preferred Qualifications :

- Experience with multimodal models (text/image/audio) and tool-using VLMs.

- Practical exposure to knowledge graphs (basic modeling/querying) in retrieval workflows.

- Prior work on content/marketing AI or enterprise copilots.

- Open-source contributions or relevant publications.

- Understanding of Responsible AI (evaluation, safety, governance).