Senior AI Engineer

Job not on LinkedIn

🔥 9 minutes ago

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Pennylane

WebsiteLinkedInAll Job Openings

501 - 1000 employees

Founded 2020

☁️ SaaS

💳 Fintech

🤝 B2B

SaaS • Fintech • B2B

Pennylane is a French SaaS platform that centralizes financial management, accounting, invoicing, expense management, treasury and business banking features for small and medium-sized businesses, independents and accounting firms. It provides an integrated dashboard, automated workflows, bank account and corporate cards, invoice and payment tools, and native integrations with accounting and payments partners to streamline bookkeeping and cashflow operations.

📋 Description

• Build and harden agentic loops in production, including LLM orchestration, tool calling, streaming, events, error recovery, checkpointing and resumability • Address security, permissions and cost through agentic RBAC, audit trails, isolated execution, and token and latency budgets • Own context and memory engineering, including context construction, retrieval, compaction, and short- and long-term memory • Turn business capabilities into specified, documented, versioned and tested tools exposed internally and through MCP • Steer agent behaviour through prompts, instructions, skills, planning, tool-selection strategies, guardrails and anti-prompt-injection • Establish evaluation practices using golden datasets, LLM-as-judge, human evaluation, regression tracking and error analysis • Collaborate with Product teams and accountant domain experts on ComptAssistant, Studio Assistant, MCP, document extraction, Autopilot bookkeeping and revision • Monitor AI trends, state-of-the-art models, emerging architectures, multimodal AI and optimization techniques • Own roadmap items and deliver agentic use cases end to end in production with evaluation sets and quality metrics • Improve the agent harness, evaluation practices and AI platform with engineers and data practitioners • Share learnings and best practices, and potentially recruit and mentor team members

🎯 Requirements

• 5–8 years of experience • Very strong Python skills • Hands-on experience building LLM and agentic systems at scale in production • Experience with prompting, tool use, context construction, RAG, failure handling, state and reliability • Experience with golden datasets, LLM-as-judge, human evaluation, A/B testing, regression and edge-case measurement • Good grasp of applied LLM/ML and AI infrastructure, including model serving, vector databases, cost and latency • Fluency in English • Ability to communicate with non-technical domain experts • Nice to have: model fine-tuning and post-training, including SFT, DPO and RL • Nice to have: MCP familiarity • Nice to have: Ruby familiarity • Full work authorization in France or an eligible European country • No visa sponsorship available

🏖️ Benefits

• 25 vacation days paid by Pennylane • Competitive compensation package • Company shares • Home workspace budget • Monthly coworking-space allowance • Access to 8,000 fitness spaces in Europe and more than 300 wellness activities through Gymlib • Busuu access for improving English or French • Latest Apple equipment • Remote work from an eligible European country within a maximum two-hour difference from CET • Company events, including Tech Days every 2 months and an annual company seminar • For France-based employees: 6 to 12 RTT • For France-based employees: 5 weeks of PTO • For France-based employees: lunch credits through Swile • For France-based employees: Alan Blue healthcare cover • For France-based employees: regular events in Lyon, Bordeaux, Nantes and other cities