Senior GenAI Engineer

Ascendion; Bengaluru; On-site; INR 3,000,000 - 5,200,000; Full time

Job summary

Ascendion is seeking a senior GenAI engineer to design scalable GenAI and RAG-based architectures. You will lead development using LangChain and LangGraph, build vector search systems and embedding pipelines, and deploy APIs and microservices for GenAI applications.

You will own the end-to-end lifecycle from design to monitoring, optimize performance and costs of LLM-based systems, and mentor junior engineers while collaborating with product teams.

Qualifications

• Experience designing GenAI architectures and RAG-based systems.
• Strong backend development experience in Python.
• Hands-on experience with LangChain / LangGraph and vector databases.

Responsibilities

• Design and implement scalable GenAI and RAG-based architectures.
• Lead development using LangChain / LangGraph and orchestration techniques.
• Architect and optimize vector search systems and embedding pipelines.
• Develop and deploy APIs and microservices for GenAI applications.
• Own end-to-end lifecycle: design, development, testing, deployment, monitoring.

Skills

GenAI architectures

Python backend

LLM pipelines

RAG pipelines

Cloud platforms

Docker & Kubernetes

CI/CD

Vector databases

Tools

LangChain

LangGraph

Pinecone

Weaviate

FAISS

Docker

Kubernetes

AWS

GCP

Azure

Job description

• Design and implement scalable GenAI and RAG-based architectures
• Lead development using LangChain / LangGraph and advanced orchestration techniques
• Architect and optimize vector search systems and embedding pipelines
• Develop and deploy APIs and microservices for GenAI applications
• Take ownership of end-to-end lifecycle: design, development, testing, deployment, monitoring
• Optimize performance, latency, and cost of LLM-based systems
• Mentor junior engineers and contribute to best practices
• Collaborate with product and business teams to translate requirements into AI solutions
• Strong expertise in Python and backend development
• Deep understanding of RAG pipelines and LLM architectures
• Hands-on experience with LangChain / LangGraph
• Strong experience with Vector Databases (Pinecone, Weaviate, FAISS, etc.)
• Proven experience deploying applications on cloud platforms (AWS/GCP/Azure)
• Experience with Docker, Kubernetes, CI/CD pipelines
• Solid understanding of system design and scalability
• Experience building enterprise-grade GenAI applications in production
• Familiarity with LLMOps / MLOps practices
• Exposure to multi-agent systems
• Experience with monitoring tools and observability