Senior GenAI Architect Production LLMs

We're committed to bringing passion and customer focus to the business.

Key Responsibilities

It's fun to work in a company where people truly BELIEVE in what they are doing!

We're committed to bringing passion and customer focus to the business.

Lead GenAI Engineer

Fractal is a strategic AI partner to Fortune 500 companies with a vision to power every human decision in the enterprise. Fractal is building a world where individual choices, freedom, and diversity are the greatest assets. An ecosystem where human imagination is at the heart of every decision. Where no possibility is written off, only challenged to get better. We believe that a true Fractalite is the one who empowers imagination with intelligence.

Fractal has been featured as a Great Place to Work by The Economic Times in partnership with the Great Place to Work® Institute and recognized as a ‘Cool Vendor’ and a ‘Vendor to Watch’ by Gartner.

Please visit Fractal | Intelligence for Imagination for more information about Fractal

Location: Bay Area, California (Sunnyvale preferred)

Note: This position is not eligible for Immigration Sponsorship at this time.



Role Overview

You will be the hands-on technical lead for a GenAI product at the intersection of large language models and enterprise analytics. This is a builder's role. You will personally architect and ship production systems, own delivery quality, and set technical direction for a distributed engineering team. This is not an advisory or architecture-only position.



Key Responsibilities

Hands-on GenAI Engineering & Delivery

• Design, build, and ship production GenAI systems end to end. Remain hands-on in the codebase rather than directing from a distance.
• Own the architecture across LLM orchestration, retrieval, agentic workflows, evaluation, and the analytics delivery layer.
• Rapidly prototype against evolving requirements and harden successful approaches into production-ready systems.

• Set technical direction for a distributed offshore engineering team and own the quality of what ships.
• Establish evaluation, observability, and guardrails so system quality is measurable and defensible.

• 8+ years of overall engineering experience, including 4+ years of hands-on experience building, shipping, scaling, and maintaining production GenAI or LLM systems. Experience limited to prototypes, proofs of concept, or research is not sufficient.
• Demonstrated record of personally building RAG pipelines, multi-agent or agentic systems, and LLM-powered analytics or decision-support workflows, with concrete and quantified outcomes.
• Deep hands-on expertise with agent orchestration frameworks such as Lang Graph, Lang Chain, Llama Index, CrewAI, or the OpenAI or Anthropic agent SDKs.
• Practical experience with modern GenAI patterns, including tool or function calling, structured outputs, hybrid and agentic retrieval, context engineering, prompt and evaluation optimization, and multi-agent coordination.
• Hands-on experience using agentic coding harnesses and AI-assisted development tools such as Claude Code, Cursor, or equivalent as part of the build workflow.

• Strong Python skills and solid backend engineering fundamentals, including REST and streaming API design, asynchronous patterns, and containerized deployment with Docker and Kubernetes.
• Production experience with LLM evaluation and observability, including offline and online evaluations, tracing, hallucination measurement, and quality measurement using RAGAS, Lang Smith, or equivalent tools.
• Sufficient fluency in data science, machine learning, and business intelligence to reason about analytical accuracy, data quality, and output…