• Research and design novel AI architectures (e.g. alternatives to standard Transformer designs, long-context models, efficient sequence modeling, hybrid architectures) • Explore architectural improvements for scalability, efficiency, and stability • Prototype and evaluate new architectures through ablations, benchmarks, and empirical studies • Author and co-author research papers for top ML conferences and journals • Collaborate with engineering teams to translate research into training and inference systems • Stay current with state-of-the-art research and identify promising directions early

This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description We’re building several LLM-powered copilots across critical workflows (e.g., underwriting productivity, agent enablement, customer support, operations/compliance, fraud). We need an AI engineer to own the LLM + retrieval + context layer that makes these copilots accurate, auditable, fast, and cost-efficient. Typical stack: Python/FastAPI, Postgres + vector (pgvector/Pinecone/Weaviate), OpenSearch, optional graph DB, Kubernetes + GPUs, OTEL/Datadog - Production RAG: indexing, retrieval, hybrid search, reranking, query rewriting, grounding, citations - Context Graph: entity resolution + linking + provenance; graph + vector retrieval; supports multi-hop context - LLM orchestration: tool/function calling, structured outputs, routing across model tiers, failure modes - GPU/inference cost optimization: batching, caching/KV reuse, quantization, autoscaling; optimize $/session + latency - Safety + compliance: PII/PHI handling, redaction, audit logs, deterministic replay, hallucination mitigation - LLMOps: eval harness (golden sets, regression, adversarial), monitoring for quality/cost/drift - Design/ship the end-to-end pipeline: retrieve → assemble context → generate → cite → log/monitor - Improve quality and trust via evaluation, feedback loops, and clear evidence-backed outputs - Partner with product, security, and domain teams; write crisp design docs; raise engineering bar - Ship RAG v1 with citations + measurable quality metrics - Deliver Context Graph v1 that improves retrieval on real copilot tasks - Reduce cost/latency with a concrete inference optimization plan shipped to prod Qualifications - 7+ years building production systems; 2+ years hands-on LLMs/RAG - Proven RAG experience (embeddings, vector DBs, hybrid search, reranking, eval) - Strong backend/distributed systems + observability - Track record shipping in high-stakes environments with auditability/correctness - Knowledge graph / entity resolution / provenance systems - GPU inference optimization (vLLM/TGI/TensorRT-LLM, quantization AWQ/GPTQ, batching) - Regulated domain experience (insurance/fintech/healthcare) Requirements - #LI-Remote - #LI-MK1 Benefits - The US national base salary range for this full-time position is $133,000 - $235,000. - Our salary ranges are determined by role, level, and location. - Individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. - Compensation details listed in US role postings reflect the base salary only and do not include applicable bonus, equity, or benefits. - Further details of our US benefits can be found at Ethos Careers .

• Research and develop new neural network architectures (e.g. alternatives or extensions to Transformers, recurrent / hybrid models, long-context systems) • Design and run architecture-level experiments (scaling laws, memory mechanisms, compute trade-offs) • Prototype models end-to-end — from research code to training-ready implementations • Collaborate with inference and systems engineers to ensure architectures are deployable and efficient • Analyze model behavior, failure modes, and inductive biases • Read, reproduce, and extend cutting-edge research papers • Contribute to internal research notes, benchmarks, and open-source efforts (where applicable)

• Own the strategic roadmap for key AI platforms, focusing on zero and low-code agent builders to streamline internal operations. • Manage relationships with AI platform vendors (e.g., Google, OpenAI) to oversee implementation, align roadmaps, roll out new features, and resolve technical bugs. • Provide technical expertise in building AI agents and implementing platforms; mentor and enable the AI Champion advisory group so they can empower their respective departments. • Apply agentic best practices to design and build workflows that automate complex tasks and help run the business more effectively. • Collaborate with other platform owners to test and continually enhance integrations across our tech stack, including Google Workspace, Slack, ServiceNow, and Salesforce. • Gather requirements from "champion" users and partner with the high-code agent team to test and integrate custom-built functionality into vendor platforms. • Help bridge technical gaps between Product Management and the AI Enablement team to ensure platform capabilities meet business needs.