{"id":3776538,"url":"https://alion.io/job/cogniify-mid-level-ai-engineer","title":"Mid Level AI Engineer","company":{"id":4610,"name":"Cogniify","domain":"cogniify.ai","url":"https://alion.io/company/cogniify","size_band":"51-200","is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Amazon ECS","optional":false},{"name":"Anthropic","optional":false},{"name":"Asyncio","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"AWS Lambda","optional":false},{"name":"Claude","optional":false},{"name":"Claude Code","optional":false},{"name":"Function Calling","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Mypy","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenAI Agents SDK","optional":false},{"name":"Pytest","optional":false},{"name":"Python","optional":false},{"name":"Amazon CloudWatch","optional":true},{"name":"CI/CD","optional":true},{"name":"IAM","optional":true},{"name":"JavaScript","optional":true},{"name":"Node JS","optional":true},{"name":"Prompt Caching","optional":true}],"status":"live","first_seen_at":"2026-11-04T17:34:57Z","employer_posted_date":null,"last_verified_at":"2026-11-04T17:34:57Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"The Role\n\nWe 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.\n\nYou 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.\n\nYou 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.\n\nWhat You'll Do\nThese 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.\nRuntime 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.\nTrust 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.\nMCP Gateway: Build and test the storefront MCP server path for Managed Agents behind an authenticating gateway, supporting vault-credential and signed-claim identity options.\nMCP 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.\nIntegration 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.\nToken & 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.\nAWS 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.\nEvaluation 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.\nBackend Services: Build robust backend services with typed APIs, structured audit logging, permissible-use checks, and idempotent operations.\n\nWhat We're Looking For\n3–6 years of experience building production Python microservices for modern SaaS, e-commerce, or technology backends.\nStrong Python fundamentals: async (asyncio), typed code (mypy/pydantic), pytest, and ruff. Comfortable subclassing abstract backends and mapping exceptions to structured results.\nAPI security fundamentals: OAuth 2.0 authorization flows, JWT issuance and verification, token lifecycle management, and secrets handling.\nMicroservices 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.\nLLM Tool-Calling Fundamentals: Experience integrating LLM APIs (Claude, OpenAI, Bedrock) with structured tool calling / function calling and agentic workflows.\nAbility to read an unfamiliar codebase quickly, trace execution paths, and debug issues systematically.\nAbility to work from written acceptance criteria, deliver with architectural guidance, and communicate progress and risks clearly in writing and in demos.\nStrong collaborator who can partner effectively with client engineers and internal cross-functional teams.\n\nPreferred Qualifications\nExperience with or interest in OAuth token exchange (RFC 8693) and secure delegation patterns (audience scoping, confused deputy prevention).\nProduction AWS experience (Lambda or ECS, IAM, Secrets Manager, CloudWatch).\nHands-on experience shipping tool-using LLM agents on the Claude Messages API or Agent SDK, with familiarity with prompt caching.\nBuilt or integrated Model Context Protocol (MCP) servers (streamable HTTP) with authentication layers.\nBuilt or extended an automated LLM evaluation or regression harness in CI/CD.\nFamiliarity with the Claude Managed Agents beta (agents, environments, sessions, vaults, and always_ask semantics).\nExperience authoring Claude Code plugins or skills.\nExperience with cloud model routing (Bedrock, Vertex, or Foundry).\nE-commerce domain knowledge (cart, variants, inventory, checkout hand-off) and Node.js for example storefronts.\nPrior experience at a FinTech company, high-growth startup, or consulting firm.\nActive experience using Claude or AI coding assistants for day-to-day engineering workflows.\n\nWhat You'll Own\nAn agentic-commerce trust integration package (Python)\nA Managed Agents gateway variant\nAn advisory MCP server\nA commerce-builder companion skill\nA merchant integration guide\nA demo against the retail vertical\n\nPerks And Benefits Of Working With Us\nUnlimited PTO.\nPlease ask us about our very generous parental leave, much above industry standards!\nEntrepreneurial culture where pushing limits and taking risks is everyday business.\nOpen communication with management and company leadership.\nSmall, dynamic teams = massive impact.\nMedical, Dental and Vision coverage for employees.\nAccess to Disability & Life insurance.\nMental health and wellbeing support.\nAnnual bonus program.\nEmployer Stock Purchase Program (ESPP).\nYearly team building experiences.\nMentorship and sponsorship opportunities.\nManager resources and support.\n\nWe 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.","description_format":"text","description_chars":6721,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Life insurance","Parental leave"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Commerce","MLOps","Custom Software Development","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-11-04T23:09:45Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":0,"expected_fill_days":30,"reasons":["seen:0","velocity","win:early"],"computed_at":"2026-11-05T05:54:30Z"},"pay":null,"html_url":"https://alion.io/job/cogniify-mid-level-ai-engineer","json_url":"https://alion.io/job/cogniify-mid-level-ai-engineer.json","meta":{"generated_at":"2026-11-06T01:28:22Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":2414,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-07T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":4610},"rest":"https://alion.io/mcp/rest/get_company?id=4610"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcogniify-mid-level-ai-engineer"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fcogniify-mid-level-ai-engineer"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fcogniify-mid-level-ai-engineer"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/cogniify-mid-level-ai-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcogniify-mid-level-ai-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3776538}},{"tool":"search_jobs","arguments":{"company":"cogniify.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3776538},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}