ML Engineer, Agentic Systems

Viridien • Houston, TX

1d

About The Position

Viridien is hiring an ML Engineer to build production agentic applications that automate complex geoscience workflows. The role involves designing agent-based systems, integrating tools and external APIs, implementing persistent state management, providing agents with relevant context, and delivering well-tested services with lightweight web interfaces for operators and end users. The engineer will help determine which workflows to automate, where people should remain in the loop, and how results should be presented and verified. They will also design and execute LLM fine-tuning strategies when model adaptation is needed.

The position is part of a collaborative team building tools and platforms across scientific seismic algorithms, data visualization, and web applications. The role works with domain experts, product, and engineering colleagues, and includes presenting design documents and trade-offs. The position is based in Houston; the posting does not specify a workplace arrangement.

Requirements

• Bachelor’s degree or higher in Computer Science, Engineering, Physics, Mathematics, Geophysics, or a related field.
• Minimum cumulative GPA of 3.5 on a 4.0 scale for all earned degrees; equivalent academic grading systems for degrees obtained outside the U.S. will be considered.
• Strong programming and software engineering fundamentals, including asynchronous and concurrent programming.
• Sound design and product judgment, including the ability to explain system design choices, what was left out, and how quality is measured.
• Hands-on experience building multi-agent or graph-based LLM workflows using established frameworks or custom implementations.
• Experience designing how agents find information, including tool-based search over files, logs, and databases, and semantic retrieval with reranking when needed.
• Practical LLM fine-tuning experience, including parameter-efficient methods such as LoRA, dataset preparation and quality assurance, offline and online evaluations, and working understanding of RL-based fine-tuning and reward design.
• Experience with tracing and evaluation of LLM applications.
• Experience building web services and APIs, such as with FastAPI, and working with PostgreSQL, Docker, and Git.
• Ability to use AI coding agents such as Claude Code or Codex: understand how they work, break down tasks, guide execution, critically review output, recognize failures, and take ownership of resulting code.

Nice To Haves

• Experience designing complex agent systems, including task decomposition, parallel execution, result aggregation, and human-in-the-loop orchestration.
• Hands-on experience with LLM post-training techniques such as DPO and GRPO, including reward design for verifiable outcomes and multi-step tool use.
• Experience running enterprise-scale applications in production, including retries, idempotency, timeouts, and rate limits.
• Prior work in workflow automation.
• Exposure to geoscience or scientific computing.
• Frontend experience building lightweight operator dashboards.

Responsibilities

• Shape application logic and user experience by defining successful outcomes, removing unhelpful elements, and making outputs easy to verify.
• Design agent workflows with branches, loops, sub-workflows, and explicit routing, using the simplest structure that solves the problem.
• Implement human-in-the-loop approvals and determine which actions agents may take autonomously.
• Provide agents with relevant context through tool-based search over files, logs, code, and databases, using text search, SQL, and semantic retrieval as appropriate.
• Ground answers in cited evidence, enforce tool permissions, and guard against prompt injection and unsafe actions.
• Integrate tools and external APIs; handle concurrency, retries, and error paths.
• Implement database-backed persistence and ensure workflows can pause and resume reliably.
• Design and execute LLM fine-tuning strategies when needed, including data curation, supervised fine-tuning with parameter-efficient methods such as LoRA, preference optimization such as DPO, reinforcement learning methods such as GRPO with verifiable rewards, evaluation sets, and rollback criteria.
• Instrument agent runs with tracing and continuous evaluation, make decisions and actions auditable, and detect quality regressions early.
• Deliver production-ready services with automated tests and CI/CD, and expose APIs for other teams or systems as needed.
• Collaborate with domain experts, product, and engineering; present clear design documents and trade-offs.
• Use AI coding agents such as Claude Code or Codex responsibly by planning and directing their work, reviewing and testing their output, and remaining accountable for shipped changes.

Benefits

• 401k Retirement Plan: when employees contribute up to 5%, Viridien matches the contribution and adds an additional 2%.
• Free on-site fitness centre offering group exercise classes.
• Short-term and long-term disability coverage at no cost to the employee.
• Parental Leave Program for mothers and fathers to take time off for childbirth, adoption, and bonding with a new child.
• Pet insurance options to meet different budgets.
• Wellness Program with personal wellness resources; participation in activities can earn $65 quarterly.

What This Job Offers

• Job Type: Full-time