AI Engineer

Job Description

We’re looking for an AI Engineer to join our team as we continue to develop the first-of-its-kind Quality and Regulatory Intelligence (QRI) platform for the life sciences industry.

In this role, you will help build and deploy AI-powered capabilities that extract insights from complex regulatory datasets, inspection reports, and government data sources. You will work closely with product managers, data engineers, and software engineers to integrate LLM-powered systems into the Redica platform.

The ideal candidate maintains a high bar for engineering quality while remaining hands‑on in the code, building scalable AI services and applications that operate reliably in production environments.

• Build and deploy AI-powered applications using large language models and generative AI frameworks.
• Develop conversational systems and intelligent workflows using LLMs and agentic frameworks.
• Integrate AI capabilities into existing platform services and APIs.
• Design and implement backend APIs and services supporting AI functionality using Python and FastAPI.
• Develop microservices that enable scalable AI inference and data processing.
• Integrate AI services with other platform components to deliver end-to-end product capabilities.
• Work with structured and unstructured regulatory datasets to power AI-driven insights.
• Implement hybrid search and retrieval workflows using vector databases and graph databases.
• Integrate AI models with data pipelines and data stores to support scalable inference.
• Deploy and maintain AI systems in production environments.
• Contribute to testing, monitoring, and performance optimization of AI services.
• Assist in troubleshooting production issues related to AI systems and model inference.
• Work closely with product managers and engineering teams to translate product requirements into AI-powered solutions.
• Participate in engineering discussions, code reviews, and sprint planning.
• Contribute to continuous improvement of AI development practices and system performance.

• Ship AI-powered features used by customers within the Redica platform.
• Contribute production-ready code to backend services and frontend interfaces.
• Help integrate LLM-based capabilities into customer-facing workflows.
• Improve reliability, testing, and performance of AI-enabled services.
• Identify opportunities to automate engineering workflows using AI tools.

• Tech Savvy:
  Demonstrates strong technical proficiency in AI technologies and modern development tools, and actively adopts emerging technologies that improve system performance and engineering productivity.
• Manages Complexity:
  Works effectively within complex systems involving AI models, data pipelines, and distributed services.
• Plans and Aligns:
  Executes development tasks within defined scopes and aligns work with product and engineering priorities.
• Collaborates:
  Works effectively with cross-functional teams and contributes constructively toward shared goals.
• Manages Ambiguity:
  Adapts to evolving datasets, model approaches, and product requirements while maintaining steady development progress.
• Engaged:
  Shares our values and possesses the essential competencies needed to thrive at Redica.

• 3+ years of experience as an ML Engineer developing and product ionizing traditional ML models and/or Generative AI applications.
• Hands‑on experience in Python.
• Strong experience in building and deploying LLM and Generative AI applications at scale.
• Extensive hands‑on experience with third‑party LLM provider APIs (OpenAI, Google, Anthropic, Amazon Bedrock) and open-source LLMs (Llama, Mistral).
• Experience in building conversational systems using LLMs and agentic frameworks (Langchain, Llama Index, Langgraph, CrewAI).
• Hands‑on experience with microservices architecture and orchestration, including building backend APIs using FastAPI.
• Experience with vector databases (e.g., Pinecone), graph databases (e.g., Neo4J), and hybrid search.
• Hands‑on experience working with SQL (e.g., Postgres, Snowflake) and No
  
  SQL (e.g., DynamoDB) databases/warehouses.
• Bachelor's degree in Computer Science, Computer Engineering, or a related technical field.

• Hands‑on experience with container orchestration services on AWS (e.g., ECS and EKS) and ML deployment on AWS (AWS Sagemaker).
• Experience with both batch and event-driven application architectures and ML inference methods.