Senior AI Engineer/AI Lead

• **This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Engineer/AI Lead based in India.**
• This role offers the opportunity to lead the development of advanced AI solutions that transform healthcare and clinical research operations.
• You will design and implement intelligent multi-agent systems that improve the processing and management of safety data.
• The position combines AI engineering, large language models, cloud technologies, and regulated industry expertise.
• You will collaborate with technical teams, domain specialists, and quality stakeholders to build secure, scalable, and compliant AI platforms.
• The role provides strong ownership over architecture decisions, AI governance, validation strategies, and innovation initiatives.
• You will contribute to meaningful technology advancements while working in a fast-paced environment focused on improving patient safety.

### Accountabilities

The Senior AI Engineer/AI Lead will be responsible for designing, building, and scaling AI-driven platforms while ensuring technical excellence, regulatory alignment, and business impact. This role requires ownership of AI architecture, model implementation, evaluation frameworks, and collaboration across multidisciplinary teams.

• Design and implement multi-agent AI architectures using modern AI platforms, orchestration frameworks, and large language models.
• Define agent workflows, including orchestration strategies, communication patterns, state management, escalation handling, and audit trail capabilities.
• Develop and optimize prompt engineering strategies, including system prompts, examples, validation rules, and safety guardrails.
• Build Model Context Protocol (MCP) servers and secure integrations that enable AI agents to access enterprise applications, data sources, and services.
• Create evaluation pipelines by designing benchmarks, preparing validation datasets, and measuring model accuracy, reliability, and performance.
• Architect quality control mechanisms, including model verification, rule-based validation, and automated escalation processes.
• Support migration and improvement of existing AI solutions while enhancing prompts, workflows, and evaluation methodologies.
• Define CI/CD and MLOps strategies covering model lifecycle management, version control, monitoring, deployment pipelines, and cost optimization.
• Establish technical validation approaches aligned with regulated software standards and collaborate on qualification documentation.
• Produce and review technical documentation, including architecture decisions, AI specifications, and implementation guidelines.
• Collaborate with engineering, quality, regulatory, and business teams to ensure solutions meet compliance and operational requirements.
• Mentor junior engineers and contribute to technical strategy, innovation, and best practices across AI development initiatives.

## Requirements

The ideal candidate brings deep expertise in AI engineering, software development, and enterprise AI implementation, with the ability to deliver reliable solutions in complex and regulated environments.

• 7+ years of hands-on experience building production-grade AI or machine learning systems, including experience with large language model applications.
• Strong expertise in AI architecture, prompt engineering, LLM orchestration, and retrieval-augmented generation (RAG) approaches.
• Practical experience with large language model platforms, APIs, and frameworks for building AI-powered applications.
• Strong knowledge of AWS services, including Bedrock, Lambda, S3, IAM, CloudTrail, and cloud-based AI infrastructure.
• Experience developing multi-agent or multi-step AI workflows using frameworks such as LangGraph, LangChain, CrewAI, or similar technologies.
• Advanced Python programming skills with strong software engineering fundamentals, including API design, testing, containerization, infrastructure-as-code, and version control.
• Experience designing evaluation frameworks for AI outputs, including benchmarking, regression testing, accuracy measurement, and confidence evaluation.
• Ability to communicate complex technical concepts clearly to technical and non-technical stakeholders.
• Bachelor’s degree in Computer Science, Engineering, or a related discipline, or equivalent professional experience.
• Experience with secure enterprise integrations and scalable AI system design.

**Preferred qualifications:**

• Experience building Model Context Protocol (MCP) servers or similar AI tool-serving architectures.
• Knowledge of regulated software environments, GxP requirements, GAMP5 validation, CSV/CSA methodologies, or FDA software guidance.
• Experience with healthcare, pharmaceutical, clinical research, or other regulated industries.
• Familiarity with document processing workflows, OCR, structured data extraction, or clinical text analysis.
• Knowledge of medical coding standards or healthcare data processing workflows.
• Proven experience delivering LLM-based solutions in production environments.

## Benefits

• Flexible work arrangements, including remote work opportunities.
• Opportunity to work on innovative AI solutions with meaningful healthcare impact.
• Exposure to advanced technologies including generative AI, cloud platforms, and AI agent frameworks.
• Continuous learning and professional development opportunities.
• Collaboration with diverse global teams across technology, healthcare, and research domains.
• Opportunity to influence AI strategy, architecture, and governance practices.
• Career growth opportunities within a technology-driven environment.