Sr. Software Developer - Generative AI

Key Responsibilities

Back-End Development:

• Design and build server-side applications and RESTful APIs using Node.js and Python with FastAPI.
• Develop scalable, maintainable software solutions according to predefined architectures.
• Develop custom generative AI applications leveraging techniques such as in-context learning, RAG, vector DB, agentic frameworks, and relevant tools such as openAI API, LangSmith, LangGraph and related ecosystems.
• Implement robust testing strategies for APIs and AI components to ensure reliability and performance.

Data & Cloud Integration:

• Integrate diverse data sources, including databases, APIs, and file-based systems hosted both on-premise and on AWS.
• Deploy, monitor, and maintain application components on AWS using best practices for scalability and security.
• Work cross-functionally with AI/ML engineers and scientists, subject matter experts and business stakeholders to clarify and translate requirements into technical solutions.
• Communicate complex technical concepts clearly to non-technical stakeholders.

Technical Qualifications

Required:

• Proven experience working on generative AI application development and Large Language Models (LLMs).
• Strong background in back-end development with Node.js and Python (specifically with FastAPI).
• Experience deploying and managing applications within the AWS cloud ecosystem.
• Solid understanding of API development, data handling and scalable architectures.
• Demonstrated ability to work on R&D projects that require iterative, creative problem-solving and thinking outside the box.
• Excellent communication abilities, including ability to communicate across diverse non-technical functional lines.

Preferred:

• Hands-on experience with specific AWS services such as AWS Lambda, Amazon ECS / Fargate, Amazon S3, Amazon RDS, DynamoDB, and API Gateway.
• Experience with Infrastructure as Code (IaC) tools like AWS CDK or CloudFormation.
• Familiarity with containerization technologies (e.g., Docker).
• Knowledge of open-source LLM frameworks and prompt engineering best practices.
• Conceptual understanding of machine learning, transformer models, inference-time techniques etc.
• Experience working in the pharmaceutical industry and understanding of relevant concepts, terminology and workflows.

Location