AI Engineer II

Axle is a bioscience and information technology company that offers advancements in translational research, biomedical informatics, and data science applications to research centers and healthcare organizations nationally and abroad. With experts in biomedical science, software engineering, and program management, we focus on developing and applying research tools and techniques to empower decision‑making and accelerate research discoveries. We work with some of the top research organizations and facilities in the country including multiple institutes at the National Institutes of Health (NIH). Benefits We Offer: Paid Time Off and Paid Holidays 401K match up to 5% Educational Benefits for Career Growth Employee Referral Bonus Flexible Spending Accounts: Dependent Care Assistant Program (DCAP) Transportation Reimbursement Account (TRN) Role Summary: Axle is seeking an AI Engineer II with experience designing and delivering production AI systems to lead the development of intelligent applications that support translational research and scientific operations. This role involves architecting retrieval‑augmented generation (RAG) systems, agentic pipelines, document understanding workflows, and the shared platform services that make these systems reliable and reusable. A significant portion of this role involves working directly with clients — scientists, program managers, and operational staff — who understand the problem domain but may not have a technical background. You will partner with them to elicit requirements, translate domain needs into well‑defined technical solutions, and ensure delivered software meets their real‑world needs. The role requires a self‑directed engineer who can make sound architectural decisions, take ownership of technical components end‑to‑end, mentor junior team members, and deliver iteratively while managing client relationships and expectations. Key Responsibilities: Architect, develop, and maintain AI‑powered applications in Python, including conversational assistants, agentic tools, and retrieval‑augmented generation (RAG) systems. Design and optimize retrieval pipelines: embedding generation, vector search, hybrid search, and reranking against large domain‑specific corpora. Build document ingestion and parsing pipelines that extract structured content (text, tables, figures, citations) from scientific and technical documents for downstream use by AI systems. Integrate structured knowledge — ontologies, controlled vocabularies, and knowledge graphs — with unstructured text to produce evidence‑grounded, provenance‑aware AI outputs. Develop and operate shared platform services that accelerate delivery of new AI applications: model gateways, agent‑tool integrations, authentication, API key management, and observability. Lead technical design decisions and establish best practices for code quality, testing, evaluation, and deployment of AI systems. Provision, deploy, monitor, and troubleshoot services on Kubernetes and cloud infrastructure, including container builds, manifests, and CI/CD pipelines. Design and maintain relational and vector databases, including schema design, indexing, migrations, and incremental data updates. Define and track quality metrics for AI systems (retrieval quality, answer faithfulness, latency, cost) and drive measurable improvements over time. Engage directly with non‑technical clients to gather requirements, clarify goals, manage expectations, and validate that delivered solutions align with their objectives. Translate high‑level client and mission needs into actionable technical specifications and development plans. Mentor junior engineers and contribute to a culture of technical excellence. Participate in and help facilitate standups, sprint planning, and cross‑team review meetings across multiple project streams. Required Skills & Qualifications: 5+ years of professional experience in software development, with recent hands‑on work building AI or ML‑powered applications. Strong proficiency in Python for application development, scripting, and tooling. Demonstrated experience building retrieval‑augmented generation (RAG) systems, including embeddings, vector search, and reranking. Experience integrating large language models (LLMs) into production applications using modern agent or orchestration frameworks. Experience with vector databases and semantic search. Demonstrated experience making architectural decisions and owning technical direction for software projects. Experience with Docker, containerization workflows, and Kubernetes for deploying and operating production services. Experience with PostgreSQL and relational database design. Strong command of Linux development environments. Experience with Git/GitHub workflows, including branching, pull requests, and code review practices. Proven ability to work independently, prioritize across concurrent workstreams, and drive projects to completion with minimal oversight. Preferred Qualifications: Experience with document parsing, OCR, and layout‑aware extraction for scientific or technical documents. Familiarity with knowledge graphs, ontologies, and controlled vocabularies, including RDF, SPARQL, or graph query languages. Experience with agent‑tool integration frameworks, including the Model Context Protocol (MCP). Experience with LLM observability, tracing, and evaluation tooling. Experience with GPU computing (CUDA/NVIDIA) for embedding or inference workloads. Experience with AWS (IAM, S3, deployment, general infrastructure management). Familiarity with OIDC/OAuth authentication and API key management in production systems. Background in biomedical informatics, translational research, or health sciences. Experience with AI‑assisted development tools (e.g., Claude Code, GitHub Copilot). Familiarity with Jira or similar project management tools. Interpersonal Skills: Strong written and verbal communication skills, including the ability to convey technical concepts to non‑technical collaborators and translate domain expertise into software requirements. Skilled at requirements elicitation — able to ask the right questions, listen actively, and bridge the gap between what subject matter experts need and what engineering can deliver. Ability to work effectively across multiple teams and project streams with different leads, priorities, and cadences. Comfortable operating in a large, cross‑functional team environment where coordination and alignment are essential. Proactive in communicating progress, raising blockers, and seeking input from teammates and stakeholders. Tactful and professional when engaging with clients and external partners; able to navigate sensitive situations and elevate appropriately. Receptive to feedback and committed to iterative improvement. The diversity of Axle’s employees is a tremendous asset. We are firmly committed to providing equal opportunity in all aspects of employment and will not tolerate any illegal discrimination or harassment based on age, race, gender, religion, national origin, disability, marital status, covered veteran status, sexual orientation, status with respect to public assistance, and other characteristics protected under state, federal, or local law and to deter those who aid, abet, or induce discrimination or coerce others to discriminate. Accessibility: If you need an accommodation as part of the employment process please contact: View email address on click.appcast.io This role has a market‑competitive salary with an anticipated base compensation range listed below. Actual salaries will vary depending on a candidate’s experience, qualifications, skills, and location.

120,000 – 150,000 USD