Senior AI Engineer

Design and build autonomous agents for finance workflows such as invoice-to-pay, three-way matching, reconciliation, GL close and exception handling.

Build tool and action layers over ERP systems and enterprise applications.

Design approval workflows, human-in-the-loop checkpoints and segregation-of-duty controls.

Build robust error recovery and ensure complete auditability of agent actions.

Integrate with SAP APIs, ERP interfaces, documents and file-based systems.

Design memory and context strategies for long-running agents.

Work on context windowing, summarization, compaction, retention and forgetting policies.

Build finance knowledge graphs covering vendors, invoices, POs, GRNs, GL accounts, contracts, approvals and provenance.

Work with graph databases such as Neo4j alongside vector search.

Build and improve evaluation frameworks for production AI systems.

Create golden datasets, workflow-level metrics and regression gates.

Develop automated evaluation and judging systems calibrated against human review.

Monitor model performance and detect drift on live workloads.

Work across OpenAI, Anthropic, Google and open-weight models .

Design model routing based on quality, latency and cost, including cascading and provider failover.

Own the latency, throughput and unit economics of AI workflows at scale.

Monitor and improve p50/p95/p99 latency and cost-per-workflow.

Build and maintain APIs using FastAPI and REST .

Mentor engineers working on AI systems and contribute to engineering best practices.

5+ years of software/ML engineering experience , including 2+ years shipping LLM systems in production .

Proven experience building and deploying multi-step AI agents that perform real actions in production systems.

Strong understanding of agent failure modes, reliability and control mechanisms.

Experience designing memory and context strategies for long-running agents.

Hands-on experience building an LLM evaluation framework , including datasets, metrics and automated judging.

Experience working with at least two LLM model providers or model families .

Experience migrating or operating live LLM workloads in production.

Experience operating AI/ML systems at significant scale with measurable production outcomes.

Finance, accounting, audit or ERP/SAP domain exposure.

Experience with computer-use or browser automation agents.

Knowledge of GraphRAG and ontology design .

Experience with document AI/OCR.

Fine-tuning or serving open-weight models.

LLM observability and tracing using tools such as LangSmith, Langfuse or OpenTelemetry.

Understanding of enterprise AI security, governance and compliance.

Experience using AI coding agents as part of everyday software development.

Python | LangGraph | LangChain | OpenAI | Anthropic | Google AI | FastAPI | PostgreSQL | pgvector | Neo4j | Elasticsearch | Java/Spring Boot | React | GCP | AWS | Docker

Familiarity with our exact stack is helpful but not mandatory if you have strong experience with equivalent technologies.

You will directly contribute to building AI systems that:

Execute real finance workflows instead of simply generating recommendations.

Interact with enterprise systems such as SAP.

Process large volumes of financial documents and transactions.

Make finance operations more automated and efficient.

Operate with strong controls, auditability and human oversight.

Serve enterprise customers at scale.

Build from the ground up: Be part of a new AI vertical targeting the global market.

High-impact work: Your systems will operate on real enterprise finance workflows at scale.

Strong engineering culture: Work alongside experienced engineers and leadership from top consulting, technology and finance backgrounds.

Ownership: Own problems end-to-end rather than individual components.

Growth: Opportunity to work across AI agents, LLMs, enterprise systems, evaluation and production infrastructure.

Compensation & Equity: Competitive compensation, incentive structures and meaningful equity in an early-stage company.