Job Responsibilities

• Lead the technical design, implementation, and evolution of AEP Knowledge Base and Agentic AI systems.

• Strong background in distributed storage (Delta Lake, Iceberg), compute (Spark), data warehousing (Snowflake, BigQuery, Redshift) and cloud services (Azure, AWS, GCP).

• Work hands-on with foundation models (OpenAI, Anthropic, Llama, Gemini) and model adaptation techniques.

• Architect RAG (Retrieval-Augmented Generation) pipelines and optimize vector databases (FAISS, Pinecone, Weaviate, Milvus) for enterprise-grade AI solutions.

• Experience with foundation models (OpenAI/Anthropic/Llama/Gemini) and model adaptation techniques.

• Design and deploy high-performance, low-latency distributed systems that scale globally.

• Establish guidelines for evaluation, safety, and guardrails for system behaviour.

• Collaborate with research and product teams to integrate modern capabilities into the Platform.

• Mentor engineers, drive technical excellence, and foster a culture of continuous learning.

• Contributions to open-source projects in the agent/LLM ecosystem is desirable.

What you will need to succeed

• 15+ years in design and development of large scale data intensive distributed systems.

• 3+ years as a lead / chief architect.

• In depth work experience on technologies like Apache Spark, Delta Lake, Snowflake, Kubernetes, etc.

• In depth work experience on one or more public clouds like Azure, AWS or GCP.

• Strong background in Relational Stores (PostgreSQL, MySQL).

• Strong experience in Vector Stores (Pinecone, Weaviate, Milvus).

• Strong coding skills in Java, Scala, Python.

• Proficiency in data structures and algorithms.

• Cost consciousness around computation and memory requirements.

• Excellent communication and collaboration skills to work with multi-functional R&D teams.

• BTech/MTech/MS in Computer Science, AI/ML or related fields.