Senior Software Engineer

We are an innovative, product-led company heavily investing in the future of AI. We are looking for a Senior Software Engineer to take ownership of building and deploying cutting-edge AI solutions into real-time user applications and high-volume data pipelines.

Our engineering culture is built for speed and excellence. We are early adopters of agentic coding tools to drive development velocity and deliver value through modern agile DevOps principles (continuous delivery, rigorous metric tracking, and rapid user feedback). Our infrastructure is fully defined as code (IaC) and continuously integrated/deployed on AWS.

Key Responsibilities:

• AI Pipeline Architecture: Design and build production-grade AI/LLM processing pipelines (document ingestion, extraction, classification, summarization, and RAG) with a strict focus on reliability, throughput, and unit economics.
• End-to-End Observability: Own observability for AI workloads (structured logs, metrics, traces, prompt/response capture, token/cost attribution, and quality evals) integrated with Datadog.
• Infrastructure as Code (IaC): Build and maintain deployment and runtime infrastructure on AWS (EKS, Lambda, Step Functions, SQS/Kinesis, S3) using Terraform or AWS CDK with reusable, reviewable modules.
• CI/CD for AI: Establish automated testing, regression evals, safe rollouts (canary/blue-green), and rollback paths for both code and prompt/model changes.
• Engineering Excellence & Mentorship: Drive pipeline architecture patterns, versioning of prompts/models/datasets, and separation of batch vs. real-time paths. Mentor engineers on building maintainable, testable AI systems.
• Security & Compliance: Partner with SRE, Platform, and Product Engineering to harden shared services and embed SOC 2 compliance practices (access control, data protection) into design decisions.

Requirements:

Must-Haves:

• 7+ years of experience building production-grade distributed systems.
• 2+ years of hands-on experience operating AI/ML or LLM-based pipelines at scale.
• Deep AWS Expertise: Proven track record with EKS/Kubernetes, Lambda, Step Functions, and event-driven patterns.
• Infrastructure Mastery: Strong proficiency using Terraform or AWS CDK as your primary delivery mechanisms.
• Language Proficiency: Strong Python skills (ideally paired with TypeScript/Node) with a deep understanding of production patterns for async processing, backpressure, retries, and idempotency.
• Advanced AI Observability: Experience with observability stacks (especially LGTM) applied to probabilistic/LLM systems (evals, drift, hallucination detection, cost/latency SLOs).
• Modern AI Tech Stack: Direct experience integrating with foundation model providers (Anthropic, OpenAI, Gemini) or self-hosted inference, including prompt management, caching, guardrails, vector stores, and embeddings pipelines.

Nice-to-Haves:

• Experience with data workflow orchestration tools like Argo or Dagster.

What We Offer:

• A highly collaborative, modern engineering environment utilizing the latest AI-assisted development tools.
• True flexibility and a deep commitment to work-life balance and mental well-being.
• Competitive salary, equity options, and comprehensive benefits package.
• The autonomy to make major architectural decisions and shape the AI roadmap.