We are seeking an experienced and dedicated Retrieval-Augmented Generation (RAG) Engineer to be a part of our dynamic team and be at the forefront of innovation, working on an exciting generative AI project for a leading pharmaceutical & telecom company in the United States.
Retrieval-Augmented Generation (RAG) Engineer
We are seeking an experienced and dedicated Retrieval-Augmented Generation (RAG) Engineer to be a part of our dynamic team and be at the forefront of innovation, working on an exciting generative AI project for a leading pharmaceutical & telecom company in the United States. This is a rare opportunity to make a real impact in a cutting-edge field, with excellent compensation. Don't miss out on shaping the future of healthcare with AI! This role combines expertise in UX design, tool chain engineering, GenAI development, and data architecture. The ideal candidate will have a strong technical background, problem-solving abilities, and the ability to collaborate across teams to deliver cutting-edge solutions in Retrieval-Augmented Generation workflows.
Responsibilities
1. UX Design & Frontend Development
- Develop and design intuitive user experiences using JavaScript, HTML, and CSS.
- Build responsive and accessible frontend interfaces with frameworks like React, Vue.js, or Angular.
- Create prototypes and wireframes using tools such as Figma, Adobe XD, or Sketch.
- Integrate frontend components with backend services, ensuring seamless communication via Django Data Models, Websockets, or Async Streaming.
- Follow best practices in WCAG accessibility standards and responsive design.
- Implement and automate frontend testing using tools like Cypress or Puppeteer.
- Create and maintain UML diagrams for system visualization and planning.
2. Tool Chain Engineering & DevOps
- Design and maintain CI/CD pipelines using tools such as AWS CodePipeline or OpenShift/Tekton.
- Implement Infrastructure as Code (IaC) with tools like Terraform and Ansible.
- Manage containerized applications and orchestration with Kubernetes (OpenShift preferred).
- Monitor infrastructure health using Prometheus, Grafana, or the ELK stack.
- Write automation scripts in Python for process optimization and tool integration.
- Adopt GitOps practices using tools like Flux or ArgoCD.
- Integrate security as code practices, incorporating SAST tools for vulnerability management.
3. GenAI Development
- Develop and integrate Chat Completion APIs for generative AI solutions.
- Design and implement agentic workflows using frameworks like LangChain or LangGraph.
- Architect and deploy RAG strategies, optimizing retrieval and embedding mechanisms.
- Work hands-on with Large Language Models (LLMs) in both SaaS and on-premise environments.
- Prepare and clean datasets for LLM fine-tuning, including tokenization and feature engineering.
- Evaluate model performance using appropriate metrics and testing methodologies.
- Manage and deploy AI pipelines with MLOps frameworks like MLflow or Kubeflow.
4. Data Architecture and Management
- Design and implement messaging solutions with Message Queues (e.g., MQTT) and event systems.
- Monitor telemetry data using tools like Prometheus and Grafana.
- Optimize data storage solutions with Time Series Databases (e.g., InfluxDB, TimescaleDB).
- Integrate and analyze data using platforms like Splunk and the ELK Stack.
- Create scalable, extensible, and machine-readable data models (JSON, YAML).
- Implement ETL pipelines for data ingestion and transformation.
- Maintain data governance standards, ensuring lineage tracking and compliance adherence.
5. General and Cross-Domain Responsibilities
- Collaborate effectively using tools like Jira, Confluence, and Slack.
- Leverage AWS cloud services (preferred), with familiarity in Azure or GCP as a plus.
- Apply networking fundamentals (e.g., SDN) to ensure efficient system operations.
- Ensure solutions are developed with security best practices, including threat modeling and system hardening (CIS Benchmarks).
- Translate complex technical concepts into clear business terms for stakeholders.
Requirements:
- Bachelor’s Degree in Computer Science, or related field
- 1+ years of industry experience
- Proven experience in UX design, DevOps, GenAI development, and data architecture.
- Strong hands-on experience with the tools and technologies outlined above.
- Proficiency in scripting and automation, particularly with Python.
- Experience working with large-scale AI/ML systems and related infrastructure.
- Familiarity with secure coding practices and system observability.
- Strong problem-solving and communication skills with an ability to collaborate cross-functionally.
Nice-to-Have Skills:
- Experience with Kubernetes orchestration on OpenShift.
- Hands-on work with LangGraph for RAG workflows.
- Familiarity with security as code integrations and advanced GitOps methodologies.
- Exposure to additional cloud platforms like Azure or GCP.
Why Join Us?
- Be a part of groundbreaking projects that shape the future of technology and healthcare.
- Work in a collaborative, innovative environment with industry-leading experts.
- Enjoy competitive compensation and growth opportunities.
- You work remotely.
Applicants are asked to submit their CVs no later than January 31, 2025. We thank all applicants; however shortlisted candidates will be contacted.