Senior AI Engineer/AI Lead
Parexel International Corporation1 month ago
Remote, India +2 moreStaff+
Responsibilities
- Design and implement the multi-agent architecture using AWS Bedrock, AgentCore, Strands SDK, LangGraph, and Anthropic Claude.
- Define agent orchestration, inter-agent communication, state management, escalation routing, and audit-trail infrastructure.
- Own prompt engineering strategies, including system prompts, few-shot examples, and guardrails for pharmacovigilance agents.
- Architect and build Model Context Protocol servers to expose enterprise applications, data sources, and services to AI agents.
- Build evaluation pipelines with benchmarks, ground-truth datasets, accuracy and precision measurements, regression testing, and confidence calibration.
- Design quality-control layers using cross-model verification, deterministic rule engines, and auto-escalation logic.
- Migrate existing systems to Claude on Bedrock while preserving proven logic and re-engineering prompts and evaluation pipelines.
- Define CI/CD and MLOps strategies covering model and prompt versioning, pipeline deployment, monitoring dashboards, and cost tracking.
- Own technical validation aligned with GAMP5 Category 5 and produce IQ/OQ/PQ documentation with QA.
- Write and review architecture decision records, algorithm descriptions, and AI model specifications aligned with regulatory frameworks.
- Collaborate with domain experts, quality assurance, regulatory specialists, and non-technical stakeholders.
- Mentor junior engineers and help drive technical direction and innovation in regulated AI systems.
Requirements
- 7+ years of hands-on experience building production ML/AI systems, including at least 2 years working with LLMs in application-level contexts.
- Deep knowledge of Anthropic Claude APIs, prompt engineering patterns, and retrieval-augmented generation architectures.
- Practical experience with AWS services including Bedrock, Lambda, S3, IAM, and CloudTrail.
- Experience building multi-agent or multi-step LLM orchestration systems with frameworks such as LangGraph, LangChain, CrewAI, or Strands SDK.
- Strong Python and software engineering fundamentals, including API design, containerization, infrastructure-as-code, testing, and version control.
- Experience designing LLM evaluation frameworks covering accuracy measurement, regression testing, and confidence calibration.
- Ability to communicate technical decisions clearly to regulatory, quality, and other non-technical audiences.
- Bachelor's degree in computer science or a related field, or equivalent professional experience.
- Preferred experience designing MCP servers or equivalent tool-serving frameworks.
- Preferred familiarity with GxP environments, GAMP5 validation, CSV/CSA approaches, or FDA software guidance.
- Preferred experience with OCR, PDF extraction, email parsing, or structured extraction from unstructured clinical text.
- Preferred experience with MedDRA or other medical coding dictionaries.
- Preferred track record shipping LLM systems in regulated industries such as pharmaceutical, healthcare, or fintech.
- Exposure to pharmacovigilance, clinical safety, or healthcare data processing is preferred.
Benefits
- Flexible, growth-oriented work environment with continuous learning opportunities.
- Opportunity to contribute to clinical research automation, patient safety, and regulated healthcare innovation.
Categories