AI/ML Architect

Recodesolutions; Chennai District; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Recodesolutions seeks an experienced AI/ML Architect to lead the design and development of scalable, real-time AI systems. You will collaborate with product, data, and engineering teams to architect end-to-end solutions—from model development to production monitoring.

Responsibilities include building low-latency inference pipelines, selecting frameworks, and ensuring reliability, observability, and performance.

Qualifications

• 6+ years of experience building and deploying ML systems in production.
• Strong understanding of scalable architectures — microservices, message queues, distributed training/inference.
• Proficient in Python and popular ML/DL frameworks (scikit-learn, TensorFlow, PyTorch).
• Hands-on experience with LLMinference optimization using vLLM, TensorRT-LLM, and SGLang.
• Familiarity with vector databases, embedding-based retrieval, and RAG pipelines.
• Experience with containerized environments (Docker, Kubernetes) and managing multi-container applications.
• Working knowledge of cloud platforms (AWS, GCP, or Azure) and CI/CD practices for ML workflows.
• Exposure to edge deployments and model compression/optimization techniques.

Responsibilities

• Design and architect AI/ML systems that are scalable, low-latency, and production-ready.
• Lead development of real-time inference pipelines for voice, vision, or NLP use cases.
• Select and integrate tools, frameworks, and infrastructure (e.g., Kubernetes, Kafka, TensorFlow, PyTorch, ONNX, Triton, VLLM).
• Collaborate with data scientists and ML engineers to productionize models.
• Ensure reliability, observability, and performance of deployed systems.
• Conduct architecture reviews, POCs, and system optimizations.
• Mentor engineers and help set best practices for ML lifecycle (MLOps).

Skills

Python

ML/DL concepts

System design

Microservices

MLOps

Tools

TensorFlow

PyTorch

ONNX

Kubernetes

Docker

Kafka

vLLM

TensorRT-LLM

RAG pipelines

Vector databases

Job description

We are seeking an experienced AI/ML Architect to lead the designand development of scalable, real-time AI systems. You will work closely withproduct, data, and engineering teams to architect end-to-end solutions — frommodel development and deployment to system integration and production monitoring.

Key Responsibilities

• Design and architect AI/ML systems that are scalable, low-latency, andproduction-ready
• Lead development of real-time inference pipelines for use cases likevoice, vision, or NLP
• Select and integrate appropriate tools, frameworks, and infrastructure(e.g., Kubernetes, Kafka, TensorFlow, PyTorch, ONNX, Triton, VLLM etc.)
• Collaborate with data scientists and ML engineers to productionizemodels
• Ensure reliability, observability, and performance of deployed systems
• Conduct architecture reviews, POCs, and system optimizations
• Mentor engineers and help set best practices for ML lifecycle (MLOps)

Requirements

• 6+ years of experience buildingand deploying ML systems in production
• Strong understanding of scalablearchitectures — microservices, message queues, distributedtraining/inference
• Proficient in Python andpopular ML/DL frameworks (scikit-learn, TensorFlow, PyTorch)
• Hands-on experience with LLMinference optimization using frameworks like vLLM, TensorRT-LLM, and SGLang
• Familiarity with vectordatabases, embedding-based retrieval, and RAG pipelines
• Experience with containerizedenvironments (Docker, Kubernetes) and managing multi-container applications
• Working knowledge of cloudplatforms (AWS, GCP, or Azure) and CI/CD practices for ML workflows
• Exposure to edge deployments and model compression/optimization techniques
• Strong foundation in softwareengineering principles and system design