Senior AI Engineer, TIFIN @Work
About The Position
TIFIN @Work is an AI-native workplace platform that connects payroll, benefits, retirement plan, and outside account data across more than 225 HR and payroll systems. Its AI agents provide personalized financial and benefits guidance to employees and actionable signals to advisors. The Senior AI Engineer will own the architecture of the platform’s AI agents, designing multi-agent workflows, building systems to evaluate answer quality, and ensuring answers—especially financial figures—are grounded in traceable sources. The role offers autonomy and close collaboration with product and client-facing teams. The team is small and distributed across the US and Spain, but works in-office every day to support collaboration. It builds in short cycles, conducts design reviews, tests carefully, and adapts its practices as AI models evolve. The position focuses on production agent orchestration, robust evaluation, trustworthy retrieval, and personalized agent context. The engineer will also improve security, latency, and cost, and contribute across the stack, including backend and frontend applications, data infrastructure, and cloud systems.
Requirements
- Experience shipping agentic AI systems to real users.
- Strong understanding of orchestration, state, checkpointing, and streaming, with deep experience in LangGraph or a similar framework.
- Experience building evaluation systems, including benchmarks and golden datasets, execution-trace scoring, LLM-as-a-judge calibrated against human labels, and offline and online evaluations such as A/B tests.
- Experience using tracing and observability tools such as LangSmith, Phoenix, or Langfuse to connect production outcomes to development and create feedback loops.
- Machine learning experience fine-tuning or distilling small language models for narrow tasks such as classification, routing, or extraction, using techniques such as LoRA, QLoRA, and quantization.
- Experience serving models with inference stacks such as vLLM, TGI, or SGLang and weighing accuracy against latency and cost.
- Experience building production RAG systems using chunking, hybrid search, reranking, vector stores, grounding, and citations.
- Ability to make tool calls and structured outputs reliable using Pydantic or JSON Schema; experience treating prompts and tool contracts as versioned and tested artifacts; and understanding of how to protect PII before data reaches an external model.
- Experience shipping with more than one model provider and choosing providers based on quality, speed, cost, and reliability.
- Strong Python skills and comfort working across the stack, including FastAPI or Django, React, TypeScript, data infrastructure, and cloud.
- Ability to clearly explain decisions in writing and design reviews and to review teammates’ designs and merge requests rigorously.
- Motivation to build systems that help people make better financial decisions.
Nice To Haves
- Interest in fine-tuning and serving open-weight models.
- Interest in MCP and tool-protocol design.
- Interest in generative UI.
- Experience or interest in using AI-native development tools such as Claude Code, Cursor, or Codex.
Responsibilities
- Design and build production multi-agent workflows in which planners and specialized agents coordinate, call tools, stream responses, pause for human input, and recover reliably from checkpoints.
- Create an AI evaluation system using adversarial test sets, execution-trace scoring, calibrated LLM judges, CI regression gates, production monitoring, and a published quality score.
- Build retrieval systems that turn financial and benefits documents into grounded, cited answers using hybrid search, reranking, and thoughtful chunking, with an evidence trail for every number.
- Build the context layer that determines what each agent knows and may use.
- Improve agent security, latency, and cost through scoped permissions, validation, prompt caching, and intelligent model routing.
- Work directly with product and client-facing teams and contribute to design reviews and teammate design and merge-request reviews.
Benefits
- Meaningful equity stake as part of the overall compensation package.
- Benefits program eligibility, including 90–100% medical, vision, and dental coverage for the employee and dependents.
- Retirement benefits.
- Flexible PTO.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
