Senior Applied AI Engineer

Novara

1d•CA$144,000 - CA$165,000

About The Position

The Flex platform helps clients develop a comprehensive compliance program, leveraging technology to instill a culture of safety and maintain a productive workplace. The platform combines features that are tailored to the needs of our clientâ€™s business, including audits and inspections, incident management, flexible training, and reporting and insights. We are seeking a highly motivated, hands-on, production-proven Senior Applied AI Engineer to drive the technical realization of our Agentic AI Platform. In this role, you will lead the design, development, and scaling of this platform, transforming our mature, traditional Enterprise EHS/ESG SaaS system (Flex) into a dynamic, AI-native system of intelligence and action. You are a developer-first engineer who is comfortable writing complex state-machine routing code in Python, deploying auto-scaling serverless pipelines on AWS, configuring secure vector search engines, and designing dynamic widget-rendering APIs for the frontend. You have built and shipped enterprise-grade AI products to production, managing the real-world challenges of multi-tenancy, PII redaction, token costs, latency, and model hallucination.

Requirements

5+ years of software development experience, with at least 2 years spent building and scaling production-grade AI features in a cloud-native SaaS environment.
Strong academic background in Computer Science, Data Science, Software Engineering, or a highly quantitative field (e.g., Mathematics, Physics, Statistics).
Hands-on, production experience with Python (Expert/Senior level).
Hands-on, production experience with LangGraph, LangChain, Vercel AI SDK or equivalent.
Hands-on, production experience with AWS infrastructure: Amazon Bedrock, ECS Fargate, S3, SQS, EventBridge, KMS, AWS Lambda, Amazon Comprehend, IAM.
Hands-on, production experience with PostgreSQL / pgVector, Amazon OpenSearch Serverless, SQLAlchemy.
Hands-on, production experience with Pandas, NumPy, PyPDF, Layout-OCR engines.
Hands-on, production experience with REST, Server-Sent Events (SSE), Webhooks, and Model Context Protocol (MCP).
Strong experience designing secure AWS architectures using Least Privilege IAM execution roles, SigV4 API signing, and KMS envelope encryption.
Experience indexing and searching datasets scaling into millions of document chunks, with a proven understanding of Direct Bulk Indexing APIs.
Solid understanding of authentication patterns (OAuth 2.0, JWT pass through) and how to isolate data logically in multi-tenant shared databases.
Demonstrated ability to write clean, unit-tested, and well-documented Python code, utilizing self-correction loops and graceful degradation patterns to handle model latency and API rate-limiting limits.
Strong communication and collaboration skills, thriving in an agile, team-based environment.

Nice To Haves

TypeScript/JavaScript experience.
Practical experience training and serving classical ML models (e.g., Isolation Forest, One-Class SVM, or unsupervised clustering) for behavioral baselining, anomaly detection, or predictive risk scoring.
Experience developing React-based micro-frontends or canvas-style Generative UI layouts.
Contributions to the open-source Model Context Protocol (MCP) ecosystem.
Background in EHS (Environmental Health & Safety) or ESG (Environmental, Social, and Governance) software systems.
AWS Certified Machine Learning â€“ Specialty or AWS Certified Solutions Architect â€“ Professional.

Responsibilities

Design and implement complex, multi-agent state machines and stateful graphs using LangGraph and LangChain to support autonomous decision-making and self-correcting loops.
Architect database-driven registries (using PostgreSQL) to dynamically discover, load, and configure agent definitions, system prompts, and task workflows at runtime without redeploying code.
Build intent-based routing engines that evaluate user queries and direct them to either deterministic execution layers (e.g., Python code interpreters running over in-memory DataFrames) or semantic retrieval layers (RAG).
Configure centralized telemetry pipelines and AI Gateways for token tracking, caching, rate limiting, and real-time streaming of internal graph execution traces (via Server Sent Events).
Build and maintain a dual-engine vector search architecture: Amazon OpenSearch Serverless for unstructured policy, regulation, and SOP document retrieval, and PostgreSQL + pgvector for structured transactional logs, incident histories, and audit records.
Build scalable, event-driven ingestion pipelines using AWS S3, SQS, EventBridge, and AWS Fargate to parse raw documents (PDF, Word, CSV) into Markdown.
Implement advanced chunking strategies, including sliding window paragraph overlaps, header breadcrumb perpetuation, and Vision Transformer (ViT) visual enrichment models to summarize embedded charts, diagrams, and stamps.
Integrate Amazon Comprehend or custom LLM classifiers inside the Fargate worker container to scrub names, emails, and SSNs before data is indexed.
Build standardized, decoupled MCP servers that wrap legacy REST APIs (Java/C# backends), exposing databases, schemas, and actions as dynamically discoverable tools for the AI agents.
Implement user-delegated token pass-through (JWT forwarding) so that data-access permissions are enforced mechanically by the legacy API. Design hard metadata filters (where tenant_id = jwt.tenant_id) in OpenSearch and pgvector to ensure multi-tenant isolation.
Configure Human-in-the-Loop (HITL) state breakpoints in LangGraph to halt write-mutations, broadcasting the pending action to administrators for UI-based approval.
Design structured JSON widget schemas (representing tables, Recharts graphs, checklists, and forms) generated dynamically by the backend agents to enable zero state rendering of layouts in the Next.js UI.