At our company, our AI settles claims in seconds and our pricing models rewrite risk in real time. We don't just talk about AI, we ship it to millions of customers every day.
Our bots handle real claims with real money. Our engineers build products that couldn't exist before LLMs and real-time data pipelines. We're turning insurance into a fully autonomous service.
The GenAI team builds conversational experiences that feel human and decision engines that learn on their own. If moving from prototype to production with millions flowing through it gets you buzzing, keep reading.
In this role you'll:
Design, build, and own end-to-end Generative-AI services from first prompt to production rollout
Combine retrieval-augmented generation (RAG), function calling, and agents to automate underwriting, claims, and customer support flows
Fine-tune open-source and commercial LLMs on proprietary datasets, evaluate with both offline benchmarks and online A/B tests
Collaborate with product, data science, and design to invent new AI-first customer experiences (and kill the bad ones fast)
Build scalable APIs and micro-services (TypeScript/NestJS or Python/FastAPI) running in Kubernetes on AWS
Instrument, monitor, and continuously improve model quality, latency, and cost you ship it, you own it
Mentor fellow engineers on GenAI best practices: prompt engineering, vector search, safety & guard-rails
Contribute to internal tooling that automates the boring stuff (CI/CD, sandbox environments, branch deploys).
Our bots handle real claims with real money. Our engineers build products that couldn't exist before LLMs and real-time data pipelines. We're turning insurance into a fully autonomous service.
The GenAI team builds conversational experiences that feel human and decision engines that learn on their own. If moving from prototype to production with millions flowing through it gets you buzzing, keep reading.
In this role you'll:
Design, build, and own end-to-end Generative-AI services from first prompt to production rollout
Combine retrieval-augmented generation (RAG), function calling, and agents to automate underwriting, claims, and customer support flows
Fine-tune open-source and commercial LLMs on proprietary datasets, evaluate with both offline benchmarks and online A/B tests
Collaborate with product, data science, and design to invent new AI-first customer experiences (and kill the bad ones fast)
Build scalable APIs and micro-services (TypeScript/NestJS or Python/FastAPI) running in Kubernetes on AWS
Instrument, monitor, and continuously improve model quality, latency, and cost you ship it, you own it
Mentor fellow engineers on GenAI best practices: prompt engineering, vector search, safety & guard-rails
Contribute to internal tooling that automates the boring stuff (CI/CD, sandbox environments, branch deploys).
Requirements:
6+ years building production-grade backend or ML systems that real users depend on
Tangible experience with LLMs prompting, fine-tuning, or deploying them behind an API (show us what you've shipped)
Fluency in at least one backend language (TypeScript, Python) and familiarity with cloud-native infra (Docker, K8s, AWS)
Strong grounding in algorithms, data structures, and probability CS, EE, Math, or equivalent real-world chops
Demonstrated skill in building resilient, high-traffic, "can't-go-down" services (finance, gaming, ad-tech, etc.)
Passion for agentic coding: chaining tools, orchestrating workflows, letting the machine do the grunt work
Curiosity, pragmatism, and the ability to learn crazy-fast (zero bureaucracy, maximum building)
Hands-on with vector databases (Pinecone, Weaviate, PGVector) or semantic search systems – an advantage
Experience implementing policy, safety, or red-teaming frameworks around GenAI – an advantage
Open-source contributions or published research in NLP / generative modeling – an advantage
Prior work with voice bots, multimodal models, or real-time streaming architectures – an advantage
Ability to work in an office environment a minimum of 3 days a week.
6+ years building production-grade backend or ML systems that real users depend on
Tangible experience with LLMs prompting, fine-tuning, or deploying them behind an API (show us what you've shipped)
Fluency in at least one backend language (TypeScript, Python) and familiarity with cloud-native infra (Docker, K8s, AWS)
Strong grounding in algorithms, data structures, and probability CS, EE, Math, or equivalent real-world chops
Demonstrated skill in building resilient, high-traffic, "can't-go-down" services (finance, gaming, ad-tech, etc.)
Passion for agentic coding: chaining tools, orchestrating workflows, letting the machine do the grunt work
Curiosity, pragmatism, and the ability to learn crazy-fast (zero bureaucracy, maximum building)
Hands-on with vector databases (Pinecone, Weaviate, PGVector) or semantic search systems – an advantage
Experience implementing policy, safety, or red-teaming frameworks around GenAI – an advantage
Open-source contributions or published research in NLP / generative modeling – an advantage
Prior work with voice bots, multimodal models, or real-time streaming architectures – an advantage
Ability to work in an office environment a minimum of 3 days a week.
This position is open to all candidates.
