• Lead the technical design, architecture, and delivery of AI solutions, with a focus on AI agents, agentic workflows, automation, and AI-assisted business processes. • Own the end-to-end engineering lifecycle of AI products: discovery, prototyping, evaluation, production implementation, rollout, monitoring, and continuous improvement. • Lead and manage an AI engineering team, including technical direction, task breakdown, mentoring, code reviews, delivery planning, and engineering quality. • Design and implement solutions using AWS AI/ML services, including Amazon Bedrock, Amazon Bedrock AgentCore, Amazon SageMaker, and other AWS services for model hosting, orchestration, data processing, monitoring, and security. • Build and integrate AI applications using technologies such as Python (FastAPI/Flask/Django) or equivalent, along with relevant AI/ML frameworks. • Design agentic systems that can interact with APIs, internal platforms, business workflows, knowledge bases, and external tools in a safe, observable, and controlled way. • Define and implement best practices for LLM application development, including prompt engineering, RAG, tool use, function calling, memory, evaluation, guardrails, and hallucination mitigation. • Drive improvements in internal engineering practices around AI-assisted development, engineering productivity, AI efficiency, automation, and responsible use of AI tools across software delivery. • Work with stakeholders to identify high-value AI use cases, assess feasibility, define success metrics, and prioritize delivery. • Establish engineering standards for AI systems, including code quality, testing, observability, reliability, security, scalability, and maintainability. • Drive MLOps and LLMOps practices, including model lifecycle management, deployment pipelines, monitoring, evaluation, drift detection, and rollback strategies. • Collaborate with DevOps, cloud, security, and platform teams to ensure AI systems are production-ready, compliant, cost-efficient, and operationally stable. • Support rollout and adoption of AI solutions across the organization, including documentation, training, stakeholder communication, and production support. • Evaluate emerging AI technologies, frameworks, models, and vendors, and provide pragmatic recommendations on adoption. • Ensure AI solutions follow responsible AI principles, including data privacy, access control, auditability, fairness, explainability where applicable, and secure handling of sensitive data.

• Advanced Prompt Engineering: Designing complex, dynamic prompt templates with conditional logic and efficiently reusing information and context within prompts to maximize generation quality and reasoning. • Structured Outputs & Schemas: Implementing various response schemes (JSON mode, function calling, Zod/JSON schemas) to ensure AI outputs are predictable and ready for seamless integration into application logic. • Prompt Engineering & Evaluations: Building robust evaluation pipelines and using Langfuse to collect feedback and score the quality of responses in real time. • Tracing & Debugging: Performing deep debugging of complex LLM chains using Langfuse traces to identify bottlenecks and optimize for cost, latency, and context window usage. • AI A/B Testing: Running systematic experiments across different models via OpenRouter (e.g., comparing Claude 3.5 Sonnet vs. GPT-4o) and analyzing results based on quantitative metrics. • Data-Driven Decisions: Making deployment decisions for new prompts or models strictly based on quantitative benchmarks and trace data, rather than intuition. • Output Scoring & Analysis: Developing scoring systems to analyze the “Problem → Solution” chain and identify root causes of hallucinations or logic errors using Langfuse analytics. • Model Performance & Fine-Tuning: Regularly re-evaluating model performance as new architectures emerge and performing fine-tuning when necessary to meet specific domain requirements.

• Design agent systems from first principles. Decide the loop, the tools, the context strategy, the evaluation harness. Choose between single-agent and multi-agent topologies, between LLM reasoning and deterministic post-passes, between retrieval and direct context loading — and defend the choice with data. • Engineer the context. The hardest part of building a good agent is what goes into the prompt and what comes out. You'll obsess over context windows, tool surfaces, structured outputs, citation grounding, and the prompt itself. • Drive evaluation rigor. Build evals before you build the agent. Diagnose where it fails, fix the root cause, and prove the fix moved the metric. • Use AI tooling like a power user. A meaningful fraction of your day will be spent driving Claude Code, Codex, and similar tools to plan, scaffold, refactor, and debug your own work. We expect you to be faster with these tools than most engineers are without them. • Become a domain expert. Healthcare claims, coding guidelines, and the medical record itself are unavoidable parts of the job. Strong engineers who lean into the domain become outsized contributors here.

Role Description Our client is hiring an AI Automation Engineer / Operator to build and deploy AI-powered tools across both the internal investment team and a portfolio of operating companies. This role exists to accelerate the firm’s modernization efforts by automating high-impact workflows related to investment research, deal structuring, outreach, reporting, and operational execution. - You will work directly with investment professionals, founders, and operators to identify business problems, design automation solutions, and ship working systems independently. - The role combines technical execution with business partnership, requiring someone who can communicate clearly, operate asynchronously, and thrive in ambiguous environments. - This is an execution-heavy role for a proactive builder who already uses AI-native tools daily and wants ownership over systems that create measurable leverage. - Candidates who thrive here are highly resourceful, curious about finance and investing, and comfortable moving between technical implementation and stakeholder conversations. Your Impact: - Build AI-powered systems that improve investment research, outreach, and deal execution workflows. - Reduce manual operational work by automating repetitive internal and portfolio company processes. - Help leadership teams identify and execute automation opportunities that create measurable business leverage. - Improve operational efficiency across multiple portfolio companies through scalable tooling and integrations. - Contribute directly to faster decision-making, improved reporting workflows, and stronger cross-functional execution. - Establish repeatable automation processes that support long-term AI adoption across the organization. Core Responsibilities - Internal Investment Team Tooling – 50% - Design, build, and maintain AI-powered internal tools that support investment research, outreach, and operational workflows. - Refine and extend an existing investor outreach web application with automated follow-up sequences and contact enrichment functionality. - Build a cap table waterfall modeling platform to streamline deal structuring and replace manual spreadsheet workflows. - Develop an AI-driven investment thesis memo generation system that aggregates research and produces firm-aligned outputs. - Identify new automation opportunities across reporting, workflow management, and investment operations. - Portfolio Company Fractional Tech Support – 50% - Serve as a fractional automation operator across portfolio companies on a project basis. - Gather requirements directly from founders and operators and translate business pain points into working AI solutions. - Build internal applications, automations, dashboards, and workflow systems tailored to portfolio company needs. - Oversee lightweight technical implementation projects and support operational deployment. - Deliver scalable systems that portfolio company teams can maintain after handoff. - Cross-Functional Communication & Business Partnership – Embedded Across Responsibilities - Collaborate with technical and non-technical stakeholders across investment and portfolio company teams. - Communicate proactively through async channels and participate in daily sync meetings. - Support ad hoc financial analysis and operational tasks using AI tools and automation workflows. - Operate with high ownership and independently scope, prioritize, and execute projects. Qualifications - 3+ years of experience in AI automation engineering, software engineering, workflow automation, or related technical roles. - Demonstrated experience building and shipping AI-powered tools, automations, or internal systems used in real business environments. - Strong Python proficiency and experience working with APIs, webhooks, and authentication flows. - Active daily use of AI-native tools such as Claude Code, Codex, Cursor, N8N, Zapier, or similar platforms. - Strong English communication skills, both written and verbal. - Ability to gather requirements, scope projects independently, and execute without heavy oversight. - Strong problem-solving skills and comfort operating in fast-paced, ambiguous environments. - Genuine interest in business operations, finance, investing, or operational strategy. - Experience collaborating cross-functionally with technical and non-technical stakeholders. Nice-to-Haves (Preferred) - Prior exposure to investment firms, private equity, hedge funds, fintech, ERP systems, or accounting platforms. - Experience working with US-based or global remote teams. - Familiarity with agent frameworks, vector databases, RAG architectures, or AI observability tools. - Basic front-end development experience using JavaScript or TypeScript. - Experience building dashboards, internal tooling, or operational reporting systems. - Educational background from a top university in your country. Tools Proficiency - Must-Haves (Required) - Claude Code - Codex - Cursor - N8N - Zapier - Python - REST APIs - Webhooks - GitHub - Signal - Nice-to-Haves (Preferred) - Make (Integromat) - JavaScript - TypeScript - AWS - Supabase - LangChain - Vector Databases - RAG Architectures - LangSmith - Langfuse Benefits - Competitive Salary: Based on experience and skills - Remote Work: Fully remote—work from anywhere - Team Incentives: Recognition for maintaining 100% CRM hygiene and on-time reporting - Generous PTO: In accordance with company policy - Health Coverage for PH-based talents: HMO coverage after 3 months for full-time employees - Direct Mentorship: Guidance from international industry experts - Learning & Development: Ongoing access to resources for professional growth - Global Networking: Connect with professionals worldwide Our Recruitment Process - Application - Screening - Skills Assessment - Top-grading Interview - Client Interview - Job Offer - Client Onboarding Ready to Join Us? If this role aligns with your skills and goals, apply now to take the next step in your journey with Pearl.