> Markdown version of [/jobs/ext/1482846-ai-software-engineer](https://www.wearedevelopers.com/jobs/ext/1482846-ai-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Software Engineer - **Company:** VELOZIENT LLC - **Location:** United States (Remote available) - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Computing Platforms, Automation of Tests, Clinical Data Repository, Code Review, Computational Biology, Continuous Integration, Data Validation, Data Infrastructure, Extract Transform Load (ETL), Data Mining, Relational Databases, Software Debugging, Web Development, Django Web Framework, Github, Python (Programming Language), NumPy, Scrum Methodology, Software Architecture, Search Technologies, Shell Script, Software Engineering, SQL Databases, ReactJS, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Pandas, Information Technology, Restful APIs, GXP, Docker - **Published:** July 29, 2026 - **Apply:** https://arc.dev/remote-jobs/j/redirect/nciqla6ixr ## About the Role We are looking for a full-time, remote AI Software Engineer with 2+ years of experience in software engineering. This role is f or an engineer who specializes in building LLM-powered product features - prompt pipelines, tool use, evaluations, and agent workflows - and who wants to apply that craft to a mission-critical life sciences product. Solid full stack fundamentals in Python are necessary. This role puts them to work at the AI layer., * Excellent English communication skills * 2+ years of professional Python experience * Hands-on experience building with LLMs: prompt engineering, structured outputs, tool/function calling, and frameworks like LangChain/LangGraph * Experience evaluating the correctness of AI responses - golden datasets, LLM-as-judge, or evaluation frameworks - and iterating on prompts and pipelines based on the results * Experience with relational databases, SQL, and Object-Relational Mappers (ORMs), including comfort writing and validating analytical SQL * Experience building web applications, especially with Django and REST APIs; enough React familiarity to collaborate across the stack * Competency with the infrastructure of software development: shell scripting, GitHub Actions, test frameworks, Docker, and CI/CD * Experience with GCP products and infrastructure such as GKE and Cloud SQL * Experience with data extraction, transformation, and loading (ETL) using numpy, Pandas (or Polars), and CSV manipulation * Experience in the life sciences and its terminology is valued Desired Experience * BS or higher in Computer Science, Data Science, or a related field (or equivalent practical experience) * Experience designing agentic AI architectures that employ graphs of agents and tools to deliver complex interactions across multiple data sources * Experience creating agentic coding workflows and AI skill definitions that accelerate overall team velocity * Experience with retrieval-augmented generation, embeddings, and vector search * Experience in regulated data environments (HIPAA, GxP, 21 CFR Part 11) or with clinical trial data standards such as CDISC/SDTM * Experience analyzing and solving software system performance problems * Experience leading a scrum team and contributing to performance conversations ## Description In this role you will build and evolve the AI systems at the conversational interface that turns natural-language questions into validated SQL analyses over clinical trial data. You'll design agent workflows, engineer prompts, build the evaluation suites that prove our AI answers are correct, and put the guardrails and oversight in place that clinical research demands. You'll have real ownership and the support to keep deepening your craft. Our client helps leading companies leverage AI to solve their hardest life sciences challenges via software platforms and strategic consulting services that enhance discoveries, expedite development, and improve outcomes with data-driven decision-making. The client team comprises creative and results-focused individuals who excel at solving real-world problems. Their diverse backgrounds bring technology and expertise from various disciplines including neuroscience, physics, engineering, computational biology, genomics, mathematics, and computer science. Responsibilities: * Understand, design, implement, and support stories ranging from small fixes to substantial features (roughly 0-21 story points), including the automated tests that prove correctness * Design, build, and support LLM-powered features: prompt engineering, structured outputs, tool/function calling, retrieval, and agent workflows built with LangChain/LangGraph * Build and maintain evaluation suites that measure the correctness of AI responses - including generated SQL - and catch regressions before customers do * Implement guardrails, human-oversight points, and production monitoring for AI features,and check prompt and context data for quality and appropriateness * Document the intended use and limitations of the AI features you build, consistent with our responsible-AI practices * Contribute readable, maintainable, and performant Python code - and help raise the bar for the codebase as a whole * Contribute to software architecture and design, and help validate designs and test plans with the team * Recognize and act on opportunities to refactor existing code to improve its readability, maintainability, and quality * Apply secure-coding practices (input validation, parameterized queries, injection prevention) and handle clinical data according to its sensitivity * Mentor less-experienced engineers and participate in the hiring and interviewing process for new teammates * Participate in code reviews and agile ceremonies: sprint planning, standups, demos, and retrospectives * Help triage and resolve production issues, debugging root causes for customer-reported problems and clearly communicating resolutions to customers and the internal team * Teach others through educational presentations in team and company venues * Contribute to internal and external documentation and knowledge base articles * Participate in blameless postmortems to identify failure points and prevent recurrence ## Related Videos - [How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge](https://www.wearedevelopers.com/videos/1328-how-to-avoid-llm-pitfalls-mete-atamel-and-guillaume-laforge) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Blueprints for Success: Steering a Global Data & AI Architecture](https://www.wearedevelopers.com/videos/1577-blueprints-for-success-steering-a-global-data-ai-architecture) - [Vectorize all the things! Using linear algebra and NumPy to make your Python code lightning fast.](https://www.wearedevelopers.com/videos/562-vectorize-all-the-things-using-linear-algebra-and-numpy-to-make-your-python-code-lightning-fast) - [Docker build without Docker](https://www.wearedevelopers.com/videos/100114-docker-build-without-docker) - [How to implement convenient Python bindings to C++](https://www.wearedevelopers.com/videos/618-how-to-implement-convenient-python-bindings-to-c) ## Related Articles - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [The Prompt Engineer ✍️](https://www.wearedevelopers.com/magazine/216-the-prompt-engineer) - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Prompt Engineering is a Job of the Past](https://www.wearedevelopers.com/magazine/342-prompt-engineering-is-a-job-of-the-past) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)