• Own AI agent projects from zero to one: problem framing, design, implementation, deployment, monitoring, and iteration • Embed with business teams to map workflows (title production, underwriting, ops), identify high-leverage bottlenecks, and streamline them using AI • Design agent architectures (tools/functions, memory/state, retrieval, guardrails) and write prompts that are testable and versioned • Build full-stack features in C# and TypeScript/React that make agents usable, safe, and fast for internal users • Ship on Azure using Microsoft/Azure AI Foundry: model selection, evaluation, deployment pipelines, and production operations • Instrument quality: define success metrics, create evals/test suites, reduce hallucinations and failure modes, and drive reliability over time • Partner with security/compliance to ensure data handling and access patterns are appropriate for enterprise workflows.

**What you'll do** - Adding AI functionality into existing Node.js / Ruby / Python / React / React Native codebases - Building LLM-powered features: chat, summaries, classification, smart search, document Q&A - Designing lightweight RAG pipelines using embeddings and vector search - Working with vector DBs (pgvector, Pinecone, Qdrant) - Implementing safe, reliable LLM endpoints (OpenAI, Anthropic, Azure) - Working with PMs and clients to shape realistic AI features and transform workflows to reduce manual effort - Advising clients when NOT to use AI and considering trade-offs related to latency, accuracy, cost and maintainability

Role Description We are looking for a Senior Engineer to lead development of Generative AI and agentic frameworks supporting enterprise-scale AI transformation. - Architect and implement GenAI and agent-based solutions - Develop scalable AI pipelines integrated with cloud platforms - Ensure governance, reliability, and performance of AI systems - Collaborate across teams to deliver enterprise AI capabilities Qualifications - Strong experience in GenAI, AI/ML, and LLM technologies - Cloud platform expertise (AWS, Azure, GCP) - Proven hands-on development experience Requirements - Experience with Python, PyTorch, LangChain, and MLOps - Data Engineering exposure: Databricks, Snowflake, Synapse, BigQuery - Alignment with cloud/data platform architecture strategies - Knowledge of Responsible AI, governance, and compliance Company Description

• The Forward Deployed AI Engineer will work directly with clients and senior engineers to build AI-powered systems inside real enterprise environments. • Understand operational workflows and convert them into technical artifacts. • Connect to real enterprise systems and data sources. • Build context-aware AI agents, retrieval systems, and automation prototypes. • Help move the best prototypes toward reliable production deployments. • Help ingest, clean, structure, and connect data from enterprise systems into context graph. • Build AI pipelines and agent-based systems that can reason over enterprise context, identify patterns, surface workflow gaps, and suggest or trigger automations. • Integrate with client infrastructure such as databases, APIs, cloud storage, document repositories, analytics tools, ticketing systems, and internal applications. • Rapidly build proof-of-concepts that show how AI can improve a client's operations. • Work with senior engineers and business stakeholders to translate ambiguous operational problems into technical designs, data models, prompts, pipelines, and deployed applications. • Help build reliable, maintainable systems that can run in production environments, including client cloud environments when needed.