Systems Developer (LLM)

Work Schedule

Environmental Conditions

Job Description

Summarized Purpose:

We are offering an outstanding opportunity to join Thermo Fisher Scientific as a Systems Developer. This role involves composing developing and maintaining Large Language Model (LLM)based systems and internal tools that boost efficiency automation and decision-making across the organization. You will be responsible for building strong secure and scalable LLM applications and integration services. Emphasis will be on quality reliability and governance as you collaborate closely with product QA and operations teams.

Education/Experience:

• Bachelors degree or comparable experience in Computer Science Information Science or a related area of study.
• Around 4 years of experience in software development systems development or backend engineering.
• At least 12 years of practical experience working with LLMs NLP or applied machine learning.

Major Job Responsibilities:

• Build and develop LLM-powered systems and services including internal tools APIs and automation workflows that address real business problems.
• Implement and maintain RAG (Retrieval-Augmented Generation) prompt orchestration and workflow pipelines that integrate LLMs with enterprise data sources and applications.
• Collaborate with partners to understand requirements and translate them into technical builds architectural diagrams and implementation plans for LLM solutions.
• Build and maintain backend services microservices and integrations (e.g. REST/GraphQL APIs) that securely connect to LLM providers and internal systems.
• Implement evaluation frameworks test harnesses and quality metrics for LLM outputs to ensure accuracy safety and consistency.
• Work closely with QA and product teams to define test strategies acceptance criteria and validation protocols for LLM workflows and user-facing features.
• Develop and maintain timely libraries system prompts and configuration artifacts ensuring version control documentation and reproducibility.
• Integrate observability and monitoring to track LLM usage performance failures and model behavior over time.
• Implement guardrails and governance mechanisms to support responsible AI use.
• Collaborate with security compliance and architecture teams to ensure data privacy access control and adherence to internal and regulatory standards.
• Use CI/CD pipelines to develop test and deliver LLM applications and services into lower and production environments.
• Continuously explore new LLM models frameworks and tools; provide recommendations and POCs to improve quality cost-efficiency and latency of LLM solutions.

Knowledge Skills and Abilities:

• Strong programming skills in Python and/or TypeScript/JavaScript with experience building backend services or automation workflows.
• Solid understanding of LLMs and NLP concepts (timely engineering tokenization embeddings RAG hallucinations evaluation metrics).
• Experience integrating with LLM platforms or APIs and working with SDKs or client libraries.
• Familiarity with vector databases / embedding stores and search paradigms.
• Experience with cloud platforms and core services such as compute storage secrets management and networking.
• Comfort with modern development practices including Git-based workflows code reviews branching strategies and unit/integration testing.
• Knowledge of security and compliance considerations for AI systems including data handling PII protection and access control.
• Strong analytical and problem-solving capabilities with the ability to debug complex distributed workflows and model behaviors.
• Effective communication and collaboration skills to work with cross-functional collaborators.

Must Have skills:

• Practical experience developing and launching features powered by large language models (chatbots copilots assistants document summarization code generation etc.).
• Strong backend development skills Proven ability to build and implement APIs services and integration layers in Python or and data integration Practical experience connecting LLMs to enterprise data via embeddings vector search or structured data integration.
• Testing and evaluation of LLMs Ability to build test cases evaluation datasets and automated checks to measure quality reliability and regressions.
• Cloud & DevOps familiarity Experience deploying and managing workloads on a leading cloud platform using CI/CD pipelines and fundamental observability techniques.

Good to have skills:

• Familiarity with LLM orchestration frameworks.
• Experience with MLOps / AIOps practices including model lifecycle management monitoring and feedback loops.
• Exposure to front-end development for building LLM-powered user interfaces.
• Knowledge of AI safety fairness and governance frameworks and experience contributing to internal guidelines or policies.
• Experience working in regulated or quality-focused environments with strong documentation and audit requirements.

Working Hours:

India: 05:30 PM to 02:30 AM IST

Philippines: 08:00 PM to 05:00 AM PST