Full-Time
Remote / Hyderabad
Senior AI Architect
We are seeking a visionary AI Architect to design and implement robust generative AI pipelines, multi-agent frameworks, and vector search infrastructure for enterprise production environments.
Role Overview
As a Senior AI Architect at AVAN, you will lead the architecture and integration of advanced machine learning models and large language models (LLMs) into client codebases. You will design retrieval-augmented generation (RAG) structures, fine-tune models on proprietary domain data, and govern LLM orchestrators like LangChain or LlamaIndex.
Key Responsibilities
- Architect, deploy, and scale multi-agent LLM systems for complex customer support and analytics automation.
- Build high-performance semantic search pipelines using vector databases such as Pinecone, Qdrant, or Milvus.
- Implement model evaluations, guardrails, and caching configurations to optimize runtime latency and token usage.
- Collaborate with backend engineers to expose model inference endpoints securely via REST and gRPC API layers.
- Conduct model training and fine-tuning experiments using PyTorch and Hugging Face pipelines.
Technical Requirements
- 5+ years of software engineering experience, with 2+ years specialized in production AI/ML applications.
- Demonstrated proficiency in Python, PyTorch, Hugging Face transformers, and LLM application frameworks.
- Hands-on experience with vector database index design, chunking policies, and metadata filtering.
- Familiarity with containerized deployments (Docker, Kubernetes) and cloud services (AWS SageMaker, GCP Vertex AI).
- Bachelor's or Master's degree in Computer Science, Data Science, Mathematics, or a related field.
Job Summary
Department
AI Centre of Excellence
Experience Level
Senior (5+ Years)
Salary Range
Competitive (based on experience)
Posted
Recently