Software Engineer - Applied AI

About the role

Niural is an AI-native platform that unifies payroll, compliance, HR and financial operations so companies can hire, pay and manage teams across 150+ countries. It is hiring a Software Engineer, Applied AI to build the intelligence layer of its platform, working on EMMA, an AI orchestration system that ships agent workflows, retrieval pipelines and document understanding systems operating on payroll, tax and compliance data. This is not a research role nor a chatbot bolted onto a SaaS product.

Key responsibilities

• Design, build and ship production LLM features including agent workflows, tool and function calling, MCP servers and RAG pipelines.
• Build retrieval systems over statutory guidance, tax authority publications, contracts and employee handbooks, owning chunking, embedding selection, hybrid search, reranking and retrieval quality.
• Build structured extraction pipelines for payroll and compliance documents such as paystubs, statutory filings and PDFs, with schema enforcement, validation and repair loops.
• Define and maintain evaluation infrastructure: golden datasets, regression suites in CI, LLM-as-judge calibration, and accuracy and hallucination rates tracked as metrics.
• Optimize latency and cost per task through model routing, prompt and semantic caching, batching and context window budgeting.
• Implement safety and correctness controls including PII detection and redaction, prompt injection defense, grounded citations, confidence thresholds and escalation to human reviewers.
• Instrument and monitor AI systems in production with tracing and observability tooling, and debug model behavior with the same rigor as application code.
• Collaborate with payroll, tax and compliance experts to turn regulatory requirements into system behavior, and with product and design to ship user-facing AI features.

Required profile

• 3+ years of professional software engineering experience, including recent production experience shipping LLM-backed features to real users.
• Strong Python skills and comfort in service-oriented codebases: APIs, queues, background workers and observability.
• Experience designing and running LLM evaluations and regression testing, not just eyeballing outputs.
• Clear written communication and a habit of documenting technical decisions.

Required skills

• Hands-on RAG: embedding models, vector stores (pgvector, OpenSearch, Pinecone or equivalent), hybrid search, reranking and query rewriting.
• Agent architectures: tool and function calling, multi-step planning, state and memory, error recovery and human-in-the-loop checkpoints.
• Structured output: JSON schema enforcement, constrained decoding, validation and repair.
• LLM observability and tracing tooling such as Langfuse, LangSmith or OpenTelemetry.
• Nice to have: AWS Bedrock, MCP servers, agent frameworks such as LangGraph, LlamaIndex or Pydantic AI, fine-tuning or distillation (LoRA/PEFT), vision-language models or OCR pipelines, React and TypeScript, fintech or regulated domain experience.

What we offer

• Competitive salary package.
• Continuous learning and career advancement programs, with mentorship and coaching.
• Supportive, collaborative work environment.
• Complimentary snacks and lunch.
• Latest MacBook Pro and a high-performance monitor provided.
• Fast-track admissions to US university Masters in CS programs for selected candidates, and visa sponsorship (L1 and Green Card) for high performers.