Huxley
Website:
huxley.com
Job details:
About the Company
We are working with an organization who is a global technology leader serving hundreds of millions of users worldwide across digital commerce, financial services, communications, and digital content. We are committed to driving innovation through advanced artificial intelligence and data-driven technologies that create meaningful impact for businesses and customers around the world.
Position Overview
As a Senior AI Engineer, you will own business unit engagements from concept to production. Working closely within product and engineering teams, you will design intelligent agents, evaluate and select appropriate models, develop prompting strategies, build tool integrations, and deploy production-ready solutions using internally hosted AI infrastructure.
You will be expected to operate independently, transforming ambiguous business requirements into measurable AI solutions while ensuring successful delivery into production environments. Beyond implementation, you will establish reusable frameworks, reference architectures, and best practices that can be leveraged across multiple teams and products.
Key Responsibilities
• Lead end-to-end AI engagements with business units, embedding directly into engineering teams and contributing production-quality code within their codebase.
• Design intelligent agent architectures, including:
- Task decomposition
- Tool and function calling
- Multi-step orchestration
- State management
- Retrieval systems
- Safety controls and guardrails
• Drive solutions from prototype to production, taking ownership of:
- Reliability
- Scalability
- Latency optimization
- Cost management
- Monitoring and observability
- Failure mode analysis
• Evaluate when agent-based solutions are appropriate versus prompting approaches, model customization, retrieval-based architectures, or conventional software solutions.
• Select and assess internal and open-source LLMs based on task-specific evaluation methodologies rather than generic benchmark performance.
• Build evaluation datasets, testing frameworks, and measurement processes in collaboration with business stakeholders.
• Lead migrations from third-party AI APIs to internally hosted AI platforms, including:
- Feature parity testing
- Prompt migration
- Staged rollout planning
- Production cutover execution
• Work closely with platform and model teams to identify gaps and drive improvements in internal AI capabilities.
• Establish prompt engineering and context engineering best practices, including:
- Structured outputs
- Tool schema design
- Retrieval optimization
- Context management
- Caching strategies
- Version control and evaluation workflows
• Diagnose quality issues and identify whether root causes stem from:
- Prompt design
- Retrieval systems
- Model behavior
- Data quality
• Develop reusable cookbooks, implementation guides, templates, and reference architectures that accelerate AI adoption across the organization.
• Provide technical leadership through:
- Code reviews
- Mentoring
- Architecture guidance
- Hands-on engineering support
Scope of the Role
This is a product-focused AI engineering position.
The role does not involve:
• Training foundation models.
• Conducting large-scale model research.
• Building core LLM platform infrastructure.
Instead, the role focuses on:
• Embedding within product and engineering teams.
• Building AI-powered applications and agents.
• Delivering production-ready solutions on top of existing AI platforms and models.
Mandatory Qualifications
• 6+ years of professional software engineering experience with recent hands-on focus on large language model applications.
• Demonstrated experience building, deploying, evaluating, and maintaining production AI agents.
• Deep practical knowledge of:
- Tool calling
- Function calling
- Multi-agent workflows
- Multi-step orchestration
- Agent reliability and failure analysis
• Strong expertise in prompt engineering and context engineering, including structured outputs, evaluation methodologies, versioning, and iterative improvement.
• Practical understanding of both open-source and commercial language models, including:
- Strengths and limitations
- Cost and latency trade-offs
- Model selection strategies
- Fine-tuning versus prompting decisions
- Retrieval-based approaches
• Strong software engineering fundamentals covering:
- Backend development
- APIs
- Testing frameworks
- Monitoring and observability
- Cloud or self-hosted inference systems
- Solutions such as vLLM or similar technologies
• Ability to work effectively within external engineering teams and communicate clearly with technical and non-technical stakeholders.
• Comfortable operating in ambiguous environments and helping define emerging processes and standards.
• Excellent written communication skills with a proven ability to create documentation, implementation guides, and technical references.
Preferred Qualifications
• Experience migrating production workloads from third-party LLM APIs to self-hosted or open-source model environments.
• Hands-on experience implementing Retrieval-Augmented Generation (RAG) systems at production scale.
• Exposure to model fine-tuning or post-training techniques sufficient to understand when such approaches are beneficial.
• Experience delivering AI solutions across globally distributed teams and multiple regions.
Click on Apply to know more.