Booth and Partners Pte Ltd - Agentic AI Developer - PH

AI Developer is needed in Philippines.

Client: Booth and Partners Pte Ltd

Location: Philippines, 00, ph

Contract: Freelance

Job Description

The Agentic AI Developer designs, builds, and operates agentic AI process automations and reusable LLM-powered components on our Azure-first stack. Partnering with Business Technology Partners (BTPs) and teams across the company, you will convert business requirements and process maps into production-grade automations that are observable, governed, and reusable. A core responsibility is rigorous quality control, which includes developing evaluation workflows, implementing hallucination detection and mitigation, measuring and reducing bias, enforcing guardrails and schema validation, and ensuring outputs are grounded, reliable, compliant, and auditable in line with SEC governance and U.S. legal requirements for registered financial advisors.

Requirements

Experience:

• 5+ years professional programming experience; 2+ years building AI tool-based solutions (LLM APIs, Copilot, ChatGPT/Claude, orchestration).
• Proven delivery of production automations on Azure and Microsoft 365 ecosystems.
• At least 2 years of experience developing solutions with AI tools (e.g., Copilot, ChatGPT, Claude, n8n, Foundry).

Technical Skills (Core):

• Languages: Python, C#, R (familiarity with JavaScript/TypeScript helpful).
• Frameworks/tools: LangChain, LangGraph, LlamaIndex, AutoGen (or similar agent frameworks); Copilot Studio, GitHub, n8n.
• Azure: Azure OpenAI, Azure AI Search/Vector, Functions, Logic Apps, Key Vault, Storage, DevOps/GitHub Actions.
• RAG pipelines, vector databases (e.g., Azure AI Search; familiarity with Pinecone/Weaviate a plus).
• API design & integration, structured outputs (JSON schema), function/tool calling.
• Observability & cost control: logging, tracing, metrics, rate/usage monitoring.

Quality Control & Evaluation:

• Ability to design and run test prompts and regression suites covering normal, edge, and adversarial scenarios.
• Skill in hallucination detection/mitigation (groundedness checks, citation requirements, retrieval confidence thresholds, fallback policies).
• Experience measuring and reducing bias (fairness metrics, scenario/corpus checks, cohort A/B testing, safe-prompting).
• Output validation using schema enforcement, tool/function results verification, and business-rule assertions.
• Building evaluation harnesses with clear SLOs/KPIs (first-pass accuracy, hallucination rate, bias indicators, latency, cost-per-task) and reporting dashboards.
• Implementing guardrails (content filters, allow/deny lists, sensitive-topic controls) and red-team testing before deployment.
• Documenting test plans, evaluation results, and traceability from requirements to acceptance criteria.

Collaboration & Compliance:

• Strong communication with BTPs/end-users; aptitude for translating requirements into technical designs and acceptance tests.
• Working knowledge of SEC governance and U.S. regulatory expectations for AI usage in financial advisory contexts; commitment to Responsible AI practices.
• Familiarity with enterprise archiving/monitoring of prompts and outputs per policy (e.g., Smarsh, Theta Lake) and change-control practices.

Nice to Have:

• Experience with real-estate AI platforms (e.g., V7, Kolena, Cadastral) or domain workflows.
• Knowledge of GenAIOps/MLOps concepts for lifecycle and evaluation (not model training).
• Containers (Docker) and CI/CD; Power Platform experience.

Additional Information

Remote Role:

• Work Hours: Must have at least 4 hours overlap with Mountain Time zone (Denver, CO).
• Communication: Strong internet connection and reliable communication tools are essential.
• Remote Work Environment: Must have a dedicated workspace free from distractions to ensure productivity.
• Cultural Sensitivity: Ability to work effectively with a diverse team and understand cultural differences.