Mid-Level AI Engineer (Python, Agent Runtimes & MCP) - USA

Cogniify, Inc.; United States; À distance; USD 126 000 - 140 000; Plein temps

Avantages offerts par ce poste

Unlimited PTO

Parental leave, generous

Health insurance

Stock options

Professional development

Résumé du poste

Cogniify, Inc. is seeking a Mid-Level AI Engineer (Python) to build the trust layer for AI shopping agents, integrating with Claude Commerce Agents and related tooling.

You will work on production Python services, MCP servers, and security-focused runtimes, delivering modular and reliable solutions for merchant teams. You’ll join a collaborative delivery team, implementing runtime setups, OAuth token exchange, and integration across AWS environments, with emphasis on API reliability and secure,

Qualifications

• 3–6 years building production Python microservices for SaaS/tech backends.
• Strong Python fundamentals: async, typed code, pytest, and ruff.
• Experience with OAuth 2.0, JWT, token lifecycle management, secrets handling.

Responsabilités

• Set up and maintain Claude runtimes and agent frameworks; ensure compatibility with code forks.
• Implement trust and identity integrations across storefront and merchant backends with secure policies.
• Build MCP server paths and tools, plus a Claude Code plugin for commerce-builder.
• Author merchant integration guides and measure integration effort as acceptance metrics.
• Integrate OAuth and enterprise identity flows to ensure trusted sessions.

Connaissances

Python

Asyncio

Typed code (mypy/pydantic)

pytest

OAuth & API security

LLM tool-calling

Cloud/AWS familiarity

Debugging & tracing code

Outils

Claude API/Agent SDK

Bedrock/AWS Lambda/ECS

CI/CD tooling

Kubernetes

Description du poste

Mid-Level AI Engineer (Python, Agent Runtimes & MCP) - USA

work Full-time distance Remote payments $126,000 – $139,500 / yr

The Role

We are looking for a Mid-Level AI Engineer (3–6 years experience) to build the trust and verification layer for AI shopping agents. You will integrate directly into Anthropic's open-source Claude Commerce Agents blueprint and the surrounding Claude tooling, making the result straightforward and modular for merchant and client engineering teams to adopt.

You will work as part of a collaborative delivery team alongside our solution architects and full-stack engineers, partnering closely with client engineering teams. The work spans production Python services, agent runtimes, MCP servers, API security, and evaluation of agent behavior.

You should be comfortable working from written epics and acceptance criteria, reading unfamiliar codebases quickly, and delivering high-quality software with clear technical direction from senior architects. Strong engineering fundamentals and sound judgment about API reliability and security failure modes matter more here than any single niche framework.

What You'll Do

These are the focus areas for your first 90 days, not an exhaustive list. Agentic commerce is moving quickly, and priorities may shift within the mission as new capabilities and protocols emerge

• Runtime Setup: Stand up the blueprint's verticals across Claude runtimes (Messages API, Agent SDK, and Managed Agents), run its test and verification suites, and maintain compatibility with our fork.
• Trust Integration: Implement the trust integration for the blueprint's StorefrontBackend and MerchantBackend. This includes binding identity at session start, executing in-path trust checks on cart and checkout hooks, mapping decisions to the blueprint's native tool-result semantics (Unavailable and domain errors), setting fail-open/fail-closed policies per hook, logging decisions without PII, and reporting outcomes.
• MCP Gateway: Build and test the storefront MCP server path for Managed Agents behind an authenticating gateway, supporting vault-credential and signed-claim identity options.
• MCP Server and Skill: Build an MCP server exposing advisory and catalog tools, plus a companion skill for the blueprint's commerce-builder Claude Code plugin.
• Integration Guide: Author the merchant integration guide and measure merchant effort (files, lines, prompt bytes, gates, and time to first verified session) as an acceptance metric.
• Token & Identity Integration: Integrate OAuth token exchange and authentication flows against enterprise identity providers, working alongside Solution Architects to ensure session trust signals use audience-scoped downstream tokens without insecure passthrough.
• AWS Runtime: Embed trust verification in agent runtimes hosted on AWS (such as Bedrock-hosted worker agents, Lambda, or ECS services), keeping enforcement logic in code outside the model.
• Evaluation Harness: Build and maintain an evaluation harness for shopping agents with scenario sets, tool-call and purchase-correctness metrics, and adversarial cases (prompt injection, wrong item, over-spend) with reproducible runs in CI.
• Backend Services: Build robust backend services with typed APIs, structured audit logging, permissible-use checks, and idempotent operations.

What We're Looking For

• 3–6 years of experience building production Python microservices for modern SaaS, e-commerce, or technology backends.
• Strong Python fundamentals: async (asyncio), typed code (mypy/pydantic), pytest, and ruff. Comfortable subclassing abstract backends and mapping exceptions to structured results.
• API security fundamentals: OAuth 2.0 authorization flows, JWT issuance and verification, token lifecycle management, and secrets handling.
• Microservices experience: service-to-service authentication, structured error and result handling across service boundaries, and the ability to call external risk APIs inside a latency budget while reasoning about fail-open versus fail-closed behavior.
• LLM Tool-Calling Fundamentals: Experience integrating LLM APIs (Claude, OpenAI, Bedrock) with structured tool calling / function calling and agentic workflows.
• Ability to read an unfamiliar codebase quickly, trace execution paths, and debug issues systematically.
• Ability to work from written acceptance criteria, deliver with architectural guidance, and communicate progress and risks clearly in writing and in demos.
• Strong collaborator who can partner effectively with client engineers and internal cross-functional teams.

Preferred Qualifications

• Experience with or interest in OAuth token exchange (RFC 8693) and secure delegation patterns (audience scoping, confused deputy prevention).
• Production AWS experience (Lambda or ECS, IAM, Secrets Manager, CloudWatch).
• Hands‑on experience shipping tool‑using LLM agents on the Claude Messages API or Agent SDK, with familiarity with prompt caching.
• Built or integrated Model Context Protocol (MCP) servers (streamable HTTP) with authentication layers.
• Built or extended an automated LLM evaluation or regression harness in CI/CD.
• Familiarity with the Claude Managed Agents beta (agents, environments, sessions, vaults, and always_ask semantics).
• Experience authoring Claude Code plugins or skills.
• Experience with cloud model routing (Bedrock, Vertex, or Foundry).
• E-commerce domain knowledge (cart, variants, inventory, checkout hand-off) and Node.js for example storefronts.
• Prior experience at a FinTech company, high‑growth startup, or consulting firm.
• Active experience using Claude or AI coding assistants for day‑to‑day engineering workflows.

What You'll Own

• An agentic-commerce trust integration package (Python)
• A Managed Agents gateway variant
• An advisory MCP server
• A demo against the retail vertical

Perks And Benefits Of Working With Us

• Unlimited PTO.
• Please ask us about our very generous parental leave, much above industry standards!
• Entrepreneurial culture where pushing limits and taking risks is everyday business.
• Open communication with management and company leadership.
• Small, dynamic teams = massive impact.
• Medical, Dental and Vision coverage for employees.
• Access to Disability & Life insurance.
• Mental health and wellbeing support.
• Employer Stock Purchase Program (ESPP).
• Yearly team building experiences.
• Mentorship and sponsorship opportunities.
• Manager resources and support.

We are an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, veteran status, or any other protected characteristic.