• 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.

Role Description We're not running an AI pilot. We're not building a chatbot. We're systematically rebuilding every repeatable workflow in the company — across Sales, Marketing, Finance, CS, HR, Legal, and Operations — on an AI-native foundation. We call this program AI Pioneer, and it is the defining internal initiative of the next 18 months at Emplifi. The Agentic Builder role is the engine of AI Pioneer. You'll be embedded directly into business teams, operating inside a federated model: - A small central hub provides governance and shared tooling (LLM gateway, eval harness, MCP server registry); you ship inside the business. - This is a hybrid role: part workflow engineer, part systems thinker, part domain translator. - Industry calls it Forward Deployed Engineer or AI Solutions Engineer. - This is not a consulting role. You don't recommend and move on; you build, you ship, and you own whether it works. What You'll Do Here - Discover & Design - Embed within business teams to map existing workflows, identify automation opportunities, and prioritise by impact and feasibility. - Translate business goals into concrete agentic workflow specifications — defining inputs, outputs, decision logic, and human-in-the-loop touchpoints. - Build & Deploy - Design and ship end-to-end AI workflows using no-code/low-code platforms (Make, or equivalent) and LLM-powered tools. - Engineer prompts as production assets — versioned, evaluated, regression-tested. - Integrate with APIs, CRMs, data warehouses, and internal tools — comfortable with JSON payloads, webhooks, and auth patterns without needing to write full backend code. - Use AI coding assistants (Claude, Gemini, ChatGPT, and Cursor) to produce, adapt, and debug scripts. - Embed & Enable - Act as the in-team AI expert for your assigned function — training colleagues, documenting workflows, and building institutional knowledge. - Collaborate with central engineering and the AI Pioneer Governance team when workflows require production infrastructure, security review, or data pipeline work. - Iterate & Scale - Maintain and improve shipped workflows based on usage feedback; establish monitoring, fallback logic, and human escalation paths. - Surface reusable patterns and components across functions, and contribute to the organisation's agentic playbook. Qualifications - Advanced prompt engineering — systematic, versioned, regression-tested. - Proficient with no-code/low-code automation tools at the complex end of the spectrum: multi-step workflows, conditionals, error handling, loops. - API literacy without hand-holding: read docs, handle OAuth/API keys, parse JSON, paginate, retry, respect rate limits. - Understands data shapes and how poorly formatted output breaks downstream steps. - Can read, lightly edit, and debug code (Python, JavaScript) produced by AI coding assistants. - Familiar with LLM concepts: context windows, temperature, tool use, structured outputs, RAG basics. - Eval and observability mindset: You instinctively reach for an eval harness before a workflow goes live. - Cost awareness: you can estimate token cost per run, spot a workflow that will bankrupt itself at scale, and choose model tier (Haiku/Sonnet/Opus or equivalent) deliberately. Requirements - Thinks in workflows, not tasks — naturally maps processes end-to-end before touching a tool. - Comfortable designing for failure: edge cases, fallback paths, and human escalation. - Can scope what should and shouldn't be automated — knows when a human decision is irreplaceable. - Can sit in a business team conversation and extract the automatable signal from the noise. - Understands enough about functional operations (finance cycles, campaign pipelines, hiring workflows, CS escalations) to build for how teams actually work, not how they say they work. - Can explain why something works (or doesn't) to people who don't code — without talking down to them or hiding behind jargon. - Recognize when a workflow touches personal data, financial data, customer data, or regulated content and route to central governance before shipping, not after. - Understand basic threat surface: prompt injection, data exfiltration via tool calls, over-permissioned agents, secret handling. - Comfortable with audit trails, access scoping, and "least privilege" defaults. - Ships working solutions — demonstrates bias toward done over perfect, with a clear standard for what 'done' means. - Owns outcomes, not just outputs — follows through on whether the automation is actually being used and delivering value. - Earns trust quickly within business teams by demonstrating domain curiosity and delivering fast. - Comfortable operating as a change agent in teams that may be skeptical — wins people over through results, not persuasion. - Knows when to escalate and involve central engineering — and how to hand off cleanly. Benefits - International and fast-paced environment - Unlimited Paid Time Off - Sick Days & Community Service Days - Multisport card - Maternity and Parental Benefit - Chance to work with the world's biggest brands at the CX tech leader - Agile and open-minded culture, with high levels of trust and flexibility - Opportunity for professional growth and development - Possibility to learn new and cutting-edge technologies, in an environment that encourages new ideas - Flexible working environment - Internal tech talks, Udemy courses, and workshops - Meetups & conferences - Possibility to work from offices in Prague (Karlin), Brno (Impact Hub), Pilsen (Roudná), or remotely within the Czech Republic - There's more as well! Speak with us to find out all the details!