Backend Software Developer - Bioinformatics and Agentic AI Focus

We’re looking for a backend developer with hands-on LLM/GenAI experience and solid prompt-engineering skills to help build data pipelines, APIs, and production AI features for bioinformatics-related projects. This is a great fit if you’re early in your career (current student or recent corporate-course/bootcamp graduate) and you loved biology/chemistry in school or university. We will teach you bioinformatics if you are willing to learn.

Open to candidates who are current BSc/MSc students or recent corporate-course/bootcamp graduates with project experience.

What you’ll do

• Design and implement backend services and APIs in Python and Node.js (JavaScript).
• Build LLM-powered features: prompt design, prompt chaining, tools/functions, and evaluation/guardrails, multimodal.
• Implement RAG pipelines (embeddings, vector databases, document preprocessing) and model-serving endpoints.
• Integrate with third-party LLMs and frameworks (e.g., OpenAI APIs, LangChain/LlamaIndex, function calling, streaming).
• Collaborate with data scientists/domain experts on bioinformatics use cases (e.g., literature mining, workflow assistants).

Minimum qualifications

• Working knowledge of Python and JavaScript/Node.js (HTTP servers, REST/GraphQL, async I/O).
• Databases: PostgreSQL, Redis; 
• Message queues (e.g., RabbitMQ, Kafka, Pub/Sub).
• Practical LLM/GenAI experience: prompt engineering, zero/few/multi-shot/chain design, calling model APIs, and basic evaluation.
• Familiarity with RAG concepts: embeddings, chunking, and at least one vector DB (FAISS, Pinecone, pgvector, etc.).
• Experience with Git, Docker, and basic CI; able to ship small services end-to-end.
• Strong sense of responsibility and accountability; you communicate clearly and follow through.

• Genuine interest in bioinformatics and life sciences; you enjoyed biology/chemistry coursework.

   

  
  Nice to have

• Cloud basics on GCP; 
• Container orchestration (ECS/Kubernetes).
• Testing frameworks (pytest, Jest), linters/formatters, and API documentation (OpenAPI/Swagger).
• Security, privacy, and data-handling best practices for healthcare/biotech contexts.
• Experience with scientific data formats (CSV/Parquet), PubMed/biomedical corpora, or simple ETL/data cleaning.
• Basic front-end skills for internal tools (React) are a plus.
• R, biopython, etc.

How we work

• Small, pragmatic teams with rapid iteration and high ownership.
• Clear deliverables, regular demos, and supportive mentorship.
• Real client impact across multiple AI projects in bioinformatics and beyond.
• Supervision by top experts in AI/Bioinformatics/Software Architecture