TixelJobs
D
Dotflixvia muse

Senior AI/ML Engineer – Generative AI, RAG & LLM

TS, INPosted 2w ago
MLOpsSeniorFull-time

About the Role

Job Summary

We are looking for experienced **Senior AI/ML Engineers** with strong hands\-on expertise in Python, Machine Learning, Generative AI, Large Language Models (LLMs), Retrieval\-Augmented Generation (RAG), and AI\-powered information extraction.

You will be responsible for developing, deploying, evaluating, and scaling production\-grade AI solutions. The role involves building LLM applications, document intelligence workflows, multi\-agent systems, and scalable AI microservices using cloud platforms and modern MLOps practices.

Candidates should have practical experience taking AI solutions from development to production and be comfortable working with cross\-functional teams in a technology consulting or B2B software environment.

Key Responsibilities

* Design, develop, deploy, and maintain production\-grade AI/ML applications, including RAG pipelines, LLM\-based applications, and automated information extraction systems.
* Build scalable, reliable, and low\-latency AI microservices using Python and REST APIs.
* Develop document intelligence workflows involving document parsing, preprocessing, chunking, embeddings, vector databases, and LLM\-based extraction.
* Implement and optimize NLP, Machine Learning, Deep Learning, and Generative AI solutions.
* Develop agentic workflows and multi\-agent applications using frameworks such as LangChain, LangGraph, and CrewAI.
* Deploy and manage AI models using AWS services, including SageMaker, Bedrock, EC2, and Lambda, and Azure services, including Azure AI Foundry and Azure OpenAI.
* Build and maintain CI/CD pipelines for AI applications using Docker, Kubernetes, GitHub Actions, and Azure DevOps.
* Implement experiment tracking, model versioning, monitoring, and deployment workflows using MLOps tools such as MLflow and Weights \& Biases.
* Establish model evaluation processes using metrics such as Precision, Recall, F1\-score, and field\-level extraction accuracy.
* Monitor application performance, reliability, latency, and service\-level objectives using tools such as Prometheus and Grafana.
* Collaborate with Product, Data Engineering, and Platform teams to convert business requirements into effective AI solutions.
* Review code, troubleshoot production issues, mentor junior engineers, and take ownership of technical deliverables.
* Stay current with developments in LLMs, NLP, document intelligence, and multi\-agent systems.

Required Skills and Qualifications1\. Programming and Machine Learning

* 3\+ years of professional AI/ML engineering experience.
* Strong proficiency in Python and SQL.
* Hands\-on experience with NumPy, pandas, and scikit\-learn.
* Experience with PyTorch or TensorFlow.
* Strong understanding of Machine Learning, Deep Learning, NLP, model evaluation, and REST API development.

2\. Generative AI, LLMs and RAG

* Practical experience building and deploying LLM\-based applications in production.
* Strong understanding of Transformer architectures, embeddings, vector databases, and RAG.
* Experience with unstructured data processing, document parsing, text chunking, and information extraction.
* Hands\-on experience developing agentic workflows or multi\-agent applications.
* Experience with LangChain, LangGraph, CrewAI, or comparable orchestration frameworks.

3\. Cloud Platforms

* Hands\-on experience with AWS AI/ML services such as SageMaker, Bedrock, EC2, or Lambda.
* Experience with Azure AI Foundry or Azure OpenAI.
* Understanding of model deployment, inference, scaling, and cloud\-based AI pipelines.

4\. MLOps and Deployment

* Experience with Docker and Kubernetes.
* Familiarity with CI/CD pipelines using GitHub Actions or Azure DevOps.
* Experience with MLflow, Weights \& Biases, or similar experiment\-tracking and model\-management tools.
* Knowledge of model monitoring, observability, automated testing, and production troubleshooting.

5\. Evaluation and Leadership

* Experience evaluating AI systems using Precision, Recall, F1\-score, an
Share