Job Title: LLM Architect-Product Engineering
Location: Pune
Employment Type: Full-Time
Experience: 8-12 Years
Domain: Generative AI / Large Language Models / AI Platforms

About the Role
We are looking for a highly experienced LLM Architect to lead the design and
implementation of scalable, production-grade Generative AI systems for our
product platform.
This is a strategic role in a product-based environment, requiring deep expertise
in Large Language Models (LLMs), prompt engineering, RAG architectures,
fine-tuning, model optimization, and enterprise AI deployment.
You will work closely with product, engineering, data science, and leadership
teams to architect AI-native capabilities that differentiate our platform in the
market.

Key Responsibilities
Architect end-to-end LLM-powered product features (chatbots, copilots,
semantic search, summarization, automation agents)
Design and implement RAG (Retrieval-Augmented Generation) pipelines
Lead LLM fine-tuning, prompt engineering, and model evaluation
strategies
Build scalable, secure, and cost-efficient AI architectures
Optimize inference performance and latency for production environments
Define LLM governance, safety, hallucination mitigation, and monitoring
frameworks

Collaborate with data engineering teams for vector database and
embedding pipelines
Evaluate open-source vs. proprietary LLM models for product integration
Mentor engineering teams and define AI architecture standards

Required Technical Skills
Core LLM Expertise
8-12 years of experience in ML / AI / Platform Engineering
Strong hands-on experience with:
Large Language Models (GPT, Llama, Mistral, etc.)
Prompt engineering & structured prompting
Fine-tuning techniques (LoRA, PEFT,



adapters)
RAG architectures
Embeddings & vector search systems
Experience integrating LLM APIs (e.g., OpenAI, Anthropic)

Programming & Frameworks
Expert-level proficiency in Python (Mandatory)
Experience with:
PyTorch / TensorFlow
Hugging Face Transformers
LangChain / LlamaIndex (or similar orchestration frameworks)
FastAPI / Flask for AI services

Data & Infrastructure
Vector databases (Pinecone, Weaviate, FAISS, Milvus, etc.)
Strong understanding of embeddings, semantic search
Cloud platforms (AWS / Azure / GCP)
Docker / Kubernetes
CI/CD for ML systems

Product & Architecture Expectations
Experience building AI features in a product-led environment
Understanding of:
Scalability & cost optimization of LLM workloads
Security & compliance considerations (especially for enterprise
customers)
Model evaluation metrics and A/B testing
Ability to design modular, reusable AI architecture components

Good to Have
Experience with multi-modal LLMs
Knowledge of Knowledge Graph + LLM hybrid systems
Exposure to edge deployment / on-prem AI solutions
Contributions to open-source AI projects
Experience working with global customers

Ideal Candidate Profile
Strong architectural mindset with hands-on coding capability
Product thinking and ability to balance innovation with reliability
Ability to translate business problems into AI-native solutions
Robust communication skills for stakeholder engagement
Experience mentoring senior engineers

Why This Role Matters
Generative AI is reshaping product ecosystems. As an LLM Architect, you will
define the AI backbone of the platform and directly influence product
differentiation, scalability, and long-term AI strategy.

📌 LLM Architect (Pune)
🏢 Datametica
📍 Pune