P

Perceptive

Imaging core labs and eClinical solutions

Agentic AI Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeRemote in UKNo salary listedRemote

About the Job

Requirements

  • Strong software engineering skills, including clean architecture, application programming interfaces, testing, and code reviews.
  • Solid grounding in retrieval-augmented generation and knowledge-grounding patterns, including chunking, embeddings, retrieval quality, citations, and traceability.
  • Familiarity with machine learning operations and DevOps practices, including continuous integration and delivery, monitoring, logging, and secure deployment practices.
  • Knowledge of data handling fundamentals, including schema design, data validation, data lineage, and auditability.
  • Strong communication skills and ability to explain technical trade-offs to non-technical stakeholders.
  • Professional software engineering experience, including shipping production systems.
  • Experience implementing large language model-based systems, including agentic workflows, tool calling, and structured outputs.
  • Practical experience evaluating large language model or agent quality using offline tests and production telemetry.
  • Demonstrated experience building or integrating AI-powered applications involving large language models, natural language processing, decision support, or automation.
  • Experience working in cross-functional environments with product and operational teams.
  • Demonstrated experience designing systems with reliability and safety in mind, including testability, monitoring, and clear failure modes.
  • A master's degree in Computer Science, Engineering, Data Science, or a related field, or equivalent practical experience.

Responsibilities

  • Partner with Product, Imaging Operations, Data Engineering, Quality Assurance, Security, and Regulatory/Quality teams to identify high-value automation opportunities and define agentic AI use cases.
  • Translate clinical-trial imaging workflows and product development life cycle processes into agent-ready task models with inputs, outputs, constraints, guardrails, and acceptance criteria.
  • Work with subject-matter experts to define quality rubrics, evaluation datasets, and human review workflows to validate agent outputs.
  • Support change management by helping teams adopt agentic features with clear user-experience patterns, onboarding, and documentation.
  • Promote engineering best practices for agentic systems, including reliability, observability, evaluation, reproducibility, and secure-by-design patterns.
  • Contribute to internal standards for prompt and version control, agent tools and plugins, retrieval configuration, grounding and citations, and human-in-the-loop review.
  • Participate in design reviews and provide guidance on selecting frameworks and architectures.
  • Coach peers through code reviews, pairing, demonstrations, and knowledge-sharing sessions.
  • Build multi-step agentic workflows with reasoning and tool use for imaging trial processes, including data intake and validation for DICOM and non-DICOM data, metadata consistency checks, protocol-driven quality-control support and discrepancy detection, data completeness checks and structured issue creation, and automated summarization of imaging packets and context generation for reviewers.
  • Implement retrieval-augmented generation patterns grounded in controlled knowledge sources such as standard operating procedures, protocols, specifications, and runbooks, with traceability.
  • Develop evaluation harnesses for agent behavior, including task success rates, hallucination and grounding checks, regression testing, and bias and failure-mode analysis.
  • Contribute production-quality code for application programming interfaces, services, and pipelines, with strong testing, documentation, and maintainability.
  • Package and deploy agentic services using approved cloud and software-development life-cycle patterns, including continuous integration and delivery, infrastructure as code, secret management, and environment promotion.
  • Implement guardrails and controls, including access control, tool permissions, sandboxing, content filtering, rate limits, and audit logging.
  • Build observability through traces, structured logs, evaluation telemetry, cost monitoring, and error analytics for agent runs, tool calls, retrieval hits, and model performance.
  • Ensure safe production operations through rollback strategies, feature flags, canary releases, and incident playbooks.
  • Stay current on agentic AI patterns, including planning, tool use, memory, multi-agent coordination, and structured outputs, and evaluate feasibility for regulated workflows.
  • Prototype and validate new capabilities quickly, then harden them into production-ready features.
  • Run experiments comparing models, prompts, retrieval strategies, and agent architectures, and document results and recommendations.
  • Identify opportunities to standardize and reuse agent components across clinical imaging workflows and product development life cycle automation.
  • Carry out other reasonable duties as requested.

Desired Qualifications

  • Exposure to medical imaging concepts, including DICOM, metadata, and modality basics, and/or clinical trial workflows.
  • Working knowledge of regulated software expectations, including a validation mindset, audit trails, and traceability.
  • Familiarity with privacy and security principles for sensitive data.
  • Ability to work across teams and iterate with end users.
  • Ability to prototype quickly and productionize reliably, with a pragmatic approach to risk and quality.
  • Experience in healthcare, life sciences, clinical trials, imaging workflows, or regulated environments.
  • A master's degree or relevant artificial intelligence/machine learning specialization.

About the Company

Perceptive

Imaging core labs and eClinical solutions

Generate a clear, concise company summary for Perceptive based on the provided description.

Company size
1,001-5,000
Company stage
Late Stage VC
Total funding
$15M
Headquarters
New Haven, CT
Founded
2000

Recently Posted Jobs

Explore more opportunities at Perceptive

See more jobs