Lead GenAI Engineer

Ascendion; Bengaluru; On-site; INR 3,500,000 - 7,000,000; Full time

Job summary

Ascendion is seeking a Lead GenAI Engineer in Bengaluru to drive architecture, design, and delivery of enterprise-scale GenAI platforms. The role demands leadership and a track record of production-grade AI systems end-to-end.

You will shape RAG and agentic workflows, scale vector retrieval, and guide LangChain/LangGraph adoption while mentoring teams and aligning AI work with business goals.

Qualifications

• Must have 7+ years of hands-on GenAI/AI engineering experience.
• Experience delivering enterprise-scale GenAI platforms end-to-end.
• Proven ability to lead architecture, design reviews, and implementation.

Responsibilities

• Define architecture and technical strategy for GenAI platforms and solutions.
• Lead design and implementation of complex RAG systems and agentic workflows.
• Drive adoption of LangChain / LangGraph and advanced LLM orchestration frameworks.
• Architect high-performance vector search and retrieval systems.
• Oversee deployment strategies, including scalable cloud-native architectures.
• Ensure reliability, observability, and governance of AI systems in production.
• Lead and mentor engineering teams; conduct design reviews and code reviews.
• Collaborate with stakeholders to align AI solutions with business goals.
• Evaluate and integrate new tools, models, and frameworks in the GenAI ecosystem.

Skills

Python

RAG & LLMs at scale

LangChain / LangGraph

Vector databases

Cloud (AWS/GCP/Azure)

Kubernetes

Microservices architecture

System design & scalability

Tools

LangChain

LangGraph

LLM orchestration frameworks

Job description

Role Overview

We are hiring a

Role Overview

We are hiring a Lead GenAI Engineer with 7–10 years of experience to drive the design, architecture, and delivery of enterprise-scale GenAI platforms. This role requires strong technical leadership and proven experience in building production-grade AI systems end-to-end.

Key Responsibilities

• Define architecture and technical strategy for GenAI platforms and solutions
• Lead design and implementation of complex RAG systems and agentic workflows
• Drive adoption of LangChain / LangGraph and advanced LLM orchestration frameworks
• Architect high-performance vector search and retrieval systems
• Oversee deployment strategies, including scalable cloud-native architectures
• Ensure reliability, observability, and governance of AI systems in production
• Lead and mentor engineering teams; conduct design reviews and code reviews
• Collaborate with stakeholders to align AI solutions with business goals
• Evaluate and integrate new tools, models, and frameworks in the GenAI ecosystem

Required Skills

• Expert-level proficiency in Python
• Extensive experience with RAG, LLMs, and prompt engineering at scale
• Strong expertise in LangChain / LangGraph and agent-based architectures
• Deep experience with Vector Databases and retrieval optimization
• Proven track record of deploying production-grade GenAI applications
• Strong experience with cloud (AWS/GCP/Azure), Kubernetes, and microservices architecture
• Solid understanding of system design, scalability, and distributed systems

Preferred Qualifications

• Experience leading GenAI/AI transformation initiatives
• Strong knowledge of LLMOps, MLOps, and governance frameworks
• Exposure to fine-tuning, evaluation frameworks, and guardrails
• Prior experience in client-facing or consulting roles

Common Must-Have Across All Roles

• Must have worked on at least one productionized AI/GenAI application
• Should have been involved in the end-to-end lifecycle:
• Problem definition → Data → Model → RAG → Deployment → Monitoring
• Strong ownership mindset and ability to work in fast-paced environments