Full Time Senior AI Engineer Jobs, in B Capital - Maukerja

Title: AI Engineer

Company: Stealth-Mode Portfolio Company

About the Company

A B Capital affiliate is working to fill several senior, founding-team roles across Dublin, Singapore, and New York. The affiliate is a confidential, stealth-mode AI company building decision intelligence for private capital markets. We're posting on their behalf while they remain in stealth. Interested candidates should apply via LinkedIn — role details below.

About us

We are an early-stage, well funded AI company building decision intelligence for private capital. Our customers are private equity and venture firms across Europe, the UK and the United States.

Investment firms make high-value decisions over long horizons and learn remarkably little from the results. The context behind each decision is scattered across email, documents and individual memory, and outcomes are almost never measured back against the original call. We are building the platform that changes that.

We build across three sites — Dublin, Singapore and New York — with Dublin as our AI focus and engineering based in both Singapore and New York.

The role

You will take AI from prototype to production: the agents, retrieval pipelines and grounded interfaces that sit in front of investors and have to be right — working from our Singapore or Dublin site.

This is a delivery role, not a research role. We need people who can lead a small team and get a high-grade system into production on a tight timeline. You will work alongside our applied AI scientists, who go deeper on extraction and evaluation methodology, and own the path from their work to something running in production.

What you will do

• Lead delivery of AI product features. Grounded chat over the firm's own history, agentic workflows, document Q&A, drafting and summarisation — with source links on every claim and sensible behaviour at the edges. Own the plan and the people delivering it, not just your own code.
• Own retrieval and context assembly in production. Chunking, embedding, hybrid search, reranking, context-window budgeting. Get the right handful of documents in front of the model, under strict permission boundaries.
• Engineer agents and tool use. Multi-step workflows, tool orchestration, structured outputs, retries and graceful failure. Make them deterministic enough to trust and cheap enough to run.
• Build the evaluation and observability layer. Offline evals wired into CI, online quality monitoring, tracing, and regression detection. If we cannot measure a change, we do not ship it.
• Manage cost and performance. Model routing, caching, batching. We are deliberately vendor-neutral across frontier and open-weight models — build so a better model is an upgrade, not a rewrite.
• Deploy alongside users directly. You will sit in real investment committees, valuation reviews and diligence processes, then take what you observed straight back into the code.

What we are looking for

Required

• 3-6+ years building production software, including real experience leading and/or working in a team and shipping high-grade AI systems to production under real time pressure — this is a delivery-focused role, not a research position.
• At least 2 years shipping LLM-powered features that real external users depended on.
• Strong Python - You can build the pipeline and the interface that consumes it.
• Heavy hands-on experience with LLM-assisted coding tools — you use them as a core part of how you and your team build, and can speak to how they change delivery speed and code review.
• Real production experience with retrieval systems — and honest views on where naive RAG breaks.
• Hands-on experience with agent frameworks, tool calling and structured output, including what goes wrong at scale.
• Rigour about evaluation. You can describe an eval harness you built and what it caught that manual spot-checking did not.
• Comfort as one of a small number of senior technical hires on your site, with your manager and closest peers in a European time zone. You need to be self-directing and a genuinely good asynchronous communicator.
• Comfort in a founding-team environment: incomplete specs, shifting priorities, direct customer contact.

Strongly preferred

• Experience with MCP or building AI interfaces consumed by third-party systems.
• Work in a domain with low tolerance for hallucination — financial services, legal, healthcare, compliance.
• Familiarity with vector and hybrid search infrastructure, and with permission-aware retrieval.
• B2B enterprise SaaS experience: SSO, RBAC, audit logging, SOC 2 or ISO 27001 readiness.
• Fine-tuning, distillation or model evaluation experience.
• Contributions to open-source AI tooling.

Process (2-3 Interviews)

1. Intro call with the hiring manager (30 min) (interview 1)
2. Technical deep dive on your prior AI Engineering work (30-45 min) (interview 2)
3. System design and research judgement session (45-60 min) (interview 2)
4. Founder conversation and team fit (45 min) (interview 3)

We aim to close within three weeks of first contact.

We are an equal opportunity employer. We are building a team from a deliberately wide range of backgrounds and will make reasonable accommodations throughout the process — just tell us what you need.

This role is at a stealth-mode company. Further detail on the product and the backing is shared under NDA at the second stage.

Interested parties, kindly apply through the link.