ML Engineer: Multi-Agent LLM Pipelines

Viridien; Houston (TX); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

401k Retirement Plan

Free on-site fitness centre

Short-term disability

Long-term disability

Parental Leave Program

Pet Insurance

Wellness Program

Job summary

Viridien in Houston is seeking an ML Engineer to build production agentic applications that automate complex geoscience workflows. You will design agent-based systems, integrate tools and external APIs, implement persistent state management, and deliver well-tested services with lightweight web interfaces for operators and end users.

Beyond implementation, you will help shape what these applications do: which workflows to automate, where people stay in the loop, and how results are presented and

Qualifications

• Bachelor’s degree or higher in CS, Engineering, Physics, Math, Geophysics, or related field.
• GPA 3.5+ on a 4.0 scale for all earned degrees; equivalent grading may apply abroad.
• Strong programming and software engineering fundamentals; asynchronous and concurrent programming.
• Hands-on experience building multi-agent or graph-based LLM workflows.
• Experience designing information retrieval for agents; tool-based and semantic search.
• LLM fine‑tuning experience incl. LoRA, dataset QA, and evals.
• Experience with tracing and evaluation of LLM applications.
• Experience building web services and APIs (FastAPI), PostgreSQL, Docker, and Git.
• Ability to guide AI coding agents, review outputs and own code.

Responsibilities

• Shape the application logic and user experience to define good results.
• Design agent workflows with branches, loops, and sub-workflows.
• Implement human-in-the-loop approvals and autonomous actions judiciously.
• Provide agents with the right context via tool-based search over files, logs, and databases.
• Ground answers in cited evidence, enforce tool permissions, guard against prompt injection.
• Integrate tools and external APIs; handle concurrency, retries, and error paths.
• Add database-backed persistence; ensure workflows pause and resume reliably.
• Design and execute LLM fine-tuning strategies and evaluation sets.
• Instrument runs with tracing, evaluation, and auditable decisions.
• Deliver production-ready services with automated tests and CI/CD.
• Collaborate with domain experts, product and engineering; write clear design docs.
• Leverage AI coding agents responsibly: plan, direct, review, and own code.

Skills

Multi-agent workflows

LLM fine-tuning

Async programming

FastAPI services

PostgreSQL

Docker

Git

Tool integration

Agent-based systems

Code ownership

Education

Bachelor's degree in CS/Engineering/Geophysics

GPA 3.5+

Tools

PostgreSQL

Docker

Git

FastAPI

Claude Code

Codex

Job description

Viridien in Houston is seeking an ML Engineer to build production agentic applications that automate complex geoscience workflows. You will design agent-based systems, integrate tools and external APIs, implement persistent state management, and deliver well-tested services with lightweight web interfaces for operators and end users.

Beyond implementation, you will help shape what these applications do: which workflows to automate, where people stay in the loop, and how results are presented and