The role leads a full-stack team building LLM and agentic AI products, from research prototypes to production SaaS and customer deployments.

Responsibilities:
Lead design, implementation, code review and delivery for the full-stack team
Mentor, unblock junior engineers and hire for the team
Build Python/FastAPI services, REST and WebSocket APIs, and agentic AI systems
Ship research and ML models into production

Required:
Expert Python, FastAPI, Linux, Docker
Production experience with agentic AI and LLM APIs
Celery, Redis or Kafka; SQL and time series databases; data pipelines
Compiling Python to binaries for customer settings
Team leadership and system design

Nice to have: local LLM deployment (vLLM, SGLang), GPU and CUDA stack, Kubernetes, cloud, CI/CD, observability.

Pay: ₹1,500,000.00 - ₹1,800,000.00 per year

Application Question(s):
Nice to have LLM deployment, GPU and CUDA stack, Kubernates, cloud, CI/CD

Work Location: Hybrid remote in Bangalore City, Bengaluru, Karnataka

📌 Lead Full Stack Developer Bengaluru
🏢 Inspity It Solutions
📍 Bengaluru