Backend Software Engineer – AI Agents
Summary
Designs and operates the AI agent layer for a seed-stage AI-native platform serving biopharma: agent runtime, tool calling, sandboxed code execution, RAG and vector search, on Python, FastAPI and Postgres. Production on-site role in Seoul (Gangnam), working daily in English with a US-based team.
Backend Software Engineer – AI Agents
Seoul, South Korea (Gangnam) | On-site | Full-time
MaxIT Consulting is looking for a Backend Engineer, Applied Agents to join a seed-stage, AI-native company building the operating system for drug programs, HQ in the San Francisco Bay Area with a team in Seoul. The platform already serves leading biopharma companies.
The Opportunity
You will design, build and operate the agent layer and the backend systems that power it: agents that carry out multi-step tasks inside real workflows, call tools reliably, run code in sandboxed environments, keep context and deliver verifiable results. This is a production role, not research demos or prototypes.
Key Responsibilities
- Build the agent runtime and harness, tool-calling infrastructure, sandboxed code execution and agent memory.
- Own reliability and observability of multi-step agent tasks.
- Design and build backend services and APIs on Python, FastAPI and Postgres.
- Design and operate vector databases, semantic search and RAG systems, tuning quality and latency.
- Build large-scale ingestion, cleaning and indexing pipelines for scientific, clinical and regulatory documents.
- Ground AI outputs in source data with traceable, verifiable citations.
- Work directly with the leadership team, domain experts and early customers, owning outcomes rather than tickets.
Required Qualifications
- 2+ years shipping and operating production backend systems end to end.
- Strong fundamentals in API design, data modeling, databases and system reliability.
- Hands-on production experience with LLM systems: RAG, vector databases and agents.
- Has built, or deeply traced, an agent runtime or harness: tool calling, sandboxing, memory.
- Ships fast on incomplete specs and uses AI coding tools (Claude Code, Cursor) daily.
- Works comfortably in English with a US-based team.
Preferred Qualifications
- Most valued: built an in-house agentic harness or internal tools to boost a team's agentic development.
- LangGraph, agent frameworks or RAG systems designed and operated in production.
- Enterprise SaaS, healthcare or life sciences products; understanding of scientific, clinical, regulatory or patent data.
- AWS, Terraform and Kubernetes in production, with reliability and observability experience.
- Seed or early-stage startup experience.
Life sciences experience is not required.
Work Arrangement
On-site role in the Seoul office (Gangnam district); fully remote is not possible. One remote day per week may be possible for a strong profile. Candidates must be based in Seoul. You will work daily in English with the US-based leadership and engineering team; US visa sponsorship may be considered after six months.
Hiring Process
Resume review, take-home assignment, two technical interviews and a cultural interview.
HOW TO APPLY
Apply through this same channel with your updated resume and your expected gross annual base salary in USD.
Skills
Sign in to read and join the discussion.