Technical Lead ((GenAI / LLMs / Django) )

Job Title: Technical Lead (GenAI / LLMs / Django)

Experience: 5+ years

Location: Noida, Sec-62 (WFO)

Company Description:

XTEN-AV is the world's leading AI-powered professional AV design platform, revolutionizing the AV industry by automating various design processes and documentation tasks. Our platform enables AV designers, integrators and manufacturers to enhance their productivity by 10X, streamlining workflows and delivering exceptional results.

About the Role

We are looking for Technical Lead who has built and shipped real-world applications using Generative AI, Large Language Models and Django. This role is not about experiments or notebooks- its about owning production-grade AI systems end to end. You will work on designing, building, and scaling AI-driven features that directly impact users, integrating LLMs deeply into backend systems, workflows and products.

Key Responsibilities

Design and build production-ready GenAI features using LLMs (OpenAI, Anthropic, open source models, etc.)

Architect and implement backend services in Django for AI-powered workflows

Develop prompting strategies, structured outputs, and guardrails for reliability

Build and maintain end-to-end AI systems (API logic persistence UI integration)

Optimize for latency, cost, and accuracy in LLM-based systems

Implement retrieval-augmented generation (RAG), embeddings, and vector search

Handle evaluation, monitoring, and iteration of AI outputs

Collaborate with product and frontend teams to ship usable AI features

Write clean, testable, and maintainable code

Required Skills & Experience

5+ years of professional experience as a software or AI engineer

Strong hands-on experience with Generative AI and LLMs

Proven experience building complete projects using: o LLM APIs o Prompt engineering o Structured JSON outputs

Strong backend experience with Python & Django

Experience integrating LLMs into real products, not just demos

Solid understanding of: o REST APIs o Databases (Postgres preferred) o Async/background processing

Comfortable working in fast-moving product environments

Nice to Have:

Experience with RAG pipelines, vector databases (Pinecone, FAISS, Weaviate, etc.)

Experience with tool calling / function calling

Familiarity with LangChain / LlamaIndex (or similar frameworks)

Experience handling prompt versioning and evaluation

Frontend exposure

Startup or SaaS experience

What Were Looking For?

Someone who ships, not just prototypes

Clear thinking around AI reliability and failure modes

Comfortable making architectural decisions

Strong ownership mindset

Ability to balance speed with correctness

What Youll Build?

AI-powered workflows and assistants

Intelligent document generation systems

Structured AI agents integrated into real products

Scalable backend systems around LLM