Job highlights

- Experience with model serving (TorchServe,TensorFlow Serving,vLLM,FastAPI) GenAI &
- LLM Expertise .

We are looking for a Platform Architect (AI/GenAI) to design and lead scalable, enterprise-grade AI/ML and LLM platforms. This role focuses on building robust data pipelines, optimizing LLM performance, and architecting cloud-native AI systems with strong MLOps and DevOps practices.

Key Responsibilities

- AI/ML &
- Data Platform Architecture Design and build scalable data pipelines for AI/ML workloads Collaborate with cross-functional teams to integrate and optimize ML models

- Develop NLP solutions (classification, sentiment analysis, topic modeling) LLM &

- GenAI Systems Design and operate LLM inference architectures (GPU optimization, quantization)

- Build RAG-based systems, chatbots, and semantic search solutions Perform prompt engineering and fine-tuning of LLMs Implement model optimization techniques (quantization, distillation) MLOps &

- DevOps Implement CI/CD pipelines (GitHub Actions, Jenkins)

- Manage Infrastructure as Code (Terraform, CloudFormation, Pulumi) Automate model training, deployment, and monitoring workflows Track experiments using MLflow or DVC Cloud &

- Infrastructure Deploy and manage systems on AWS / Azure / GCP Work with Kubernetes, Docker, Helm, and service mesh

- Ensure secure, scalable, and high-performance cloud architectures Model Evaluation &





- Optimization Design and execute A/B testing frameworks Optimize models for performance, cost, and scalability

- Required Skills Technical Skills Advanced Python programming Strong experience with Apache Spark and large-scale data processing Proficiency in SQL and data querying Experience with ML frameworks (PyTorch, TensorFlow, Hugging Face)

- Software Engineering Strong system design and architecture skills Experience with microservices and distributed systems Knowledge of Go or Rust (preferred)

- Ability to create Low-Level Design (LLD) DevOps &

- MLOps Hands-on with Terraform / CloudFormation / Pulumi Experience with CI/CD pipelines (GitHub Actions, Jenkins) Expertise in Docker, Kubernetes, Helm, service mesh

- Experience with model serving (TorchServe, TensorFlow Serving, vLLM, FastAPI) GenAI &

- LLM Expertise

- Experience with RAG, vector databases, and LLM applications Strong knowledge of prompt engineering and model optimization

- Hands-on experience building chatbots, recommendation systems Cloud &

- Security Strong experience with AWS / Azure / GCP Knowledge of cloud networking and security best practices Positive to Have Experience in healthcare AI domain Knowledge of advanced LLM optimization techniques

- Exposure to translation systems and multilingual AI Soft Skills Strong leadership and architecture mindset

- Excellent problem-solving and analytical skills Ability to mentor teams and drive technical strategy

📌 Platform Architect (AI / GenAI) (Pune)
🏢 Mobile Programming
📍 Pune