{"id":2112467,"url":"https://alion.io/job/apreel-principal-python-langgraph-engineer","title":"Principal Python + LangGraph Engineer","company":{"id":3913594,"name":"apreel","domain":"apreel.com","url":"https://alion.io/company/apreel","size_band":"201-500","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Traffit","truth_index":null},"role":"Backend","role_family":"Backend","seniority":"lead","employment_type":"contractor","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Poland"],"countries":["PL"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":160,"max":200,"currency":"PLN","period":"hour","gross":null,"usd_annual":102000},"salary_estimate":null,"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"AI Agents","optional":false},{"name":"Anthropic","optional":false},{"name":"Asyncio","optional":false},{"name":"Celery","optional":false},{"name":"Dependency Injection","optional":false},{"name":"FastAPI","optional":false},{"name":"Hallucination","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"OpenAI","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Prompt Caching","optional":false},{"name":"Pytest","optional":false},{"name":"Python","optional":false},{"name":"Redis","optional":false},{"name":"Tool Use","optional":false},{"name":"Claude","optional":true},{"name":"Dagster","optional":true},{"name":"pgvector","optional":true},{"name":"Pinecone","optional":true},{"name":"Prefect","optional":true},{"name":"Qdrant","optional":true},{"name":"RAG","optional":true}],"status":"live","first_seen_at":"2026-09-25T10:10:45Z","employer_posted_date":null,"last_verified_at":"2026-09-25T10:10:45Z","board_verified":false,"closed_at":null,"days_open":17,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":17},"description":"Engagement context\nWe are partnering with a US-based health-tech company on the takeover of a production AI-powered mobile coaching platform. The platform is built around a Python AI core (atlas-ai) which runs:\nA FastAPI chat surface with intent routing and tool-using agents\nA LangGraph-based agent framework with multi-agent orchestration\nA Celery + Redis task queue for asynchronous agent flows\nMongoDB for fitness-plan storage, Redis for conversation state, Postgres for LangGraph checkpoints\nSeveral agent personas: onboarding, chat, plan creation, in-workout smart adjust, plan smart adjust, habit formation\nDirect OpenAI integration for the LLM layer\nThis is the product. If the AI core breaks, the product breaks. If LLM token cost runs away, our margin runs away. If the agent flows behave unpredictably under load, real users get bad coaching.\nRole summary\nAs Principal AI Engineer you are the technical owner of the AI core. You lead the audit of the existing codebase, define the architecture we evolve toward, build the test and evaluation harness that lets us ship changes safely, and you are the engineer who is paged when the AI surface misbehaves in production.\nYou will be the deciding voice on whether we can responsibly take this service in our scope or whether we keep the client's original team embedded longer. The audit conclusions you write in the first 4 weeks will inform the contractual scope of the entire engagement.\nOffer:\nLocation: 100% remote\nEngagement: B2B\nRate: upt to PLN 180 p/h\nStart: asap\n\nZakres obowiązków\nAudit atlas-ai: agent flows, LangGraph state machines, Celery topology, datastore usage, OpenAI integration patterns \nProduce a written assessment of operational risk: failure modes, race conditions, retry semantics, idempotency, checkpoint integrity \nQuantify token cost per agent flow and per user session \nIdentify the highest-risk subsystems and propose stabilisation plans \nBuild (or harden) an evaluation harness for the agent flows — golden cases, regression suites, hallucination/safety tests \nLead the knowledge-transfer sessions from the client's AI team \nSet the technical direction for the AI core\nLead design for new agent flows and major changes to existing ones\nOwn the production health of the AI surface (with platform/SRE support)\nHire and mentor the rest of the AI squad (~10 engineers at full scale)\nRepresent the AI core in cross-team architecture conversations with the client\nWymagania\nMust-have skills\n7+ years Python in production at senior+ level\nDeep LangGraph experience — state graphs, checkpoints, interrupts, multi-agent supervision, subgraphs\nStrong LangChain ecosystem knowledge (chains, tools, memory, output parsers, callbacks)\nProduction FastAPI — streaming responses, dependency injection, middleware, async patterns\nCelery + Redis broker in production — task ordering, retries, idempotency, priority queues, dead-letter handling\nConcurrency in Python — asyncio (gather, structured concurrency, cancellation), threading boundaries, mixing sync and async code safely\nMulti-datastore operations — MongoDB + Redis + Postgres in a single service, transaction boundaries across them\nOpenAI API at scale — rate limits, retries with exponential backoff, fallback model routing, streaming, tool/function calling\nAgent design patterns — ReAct, plan-and-execute, supervisor patterns, tool-use loops, multi-turn state, interrupt resumption\nPrompt engineering with discipline — evaluation, A/B testing, version control of prompts, regression detection\nToken cost optimisation — prompt caching (Anthropic-style), model tiering, context window trimming, summary memory\nProduction LLM observability — per-route token spend, prompt-level tracing, drift monitoring\nTesting discipline — pytest (including pytest-asyncio), property-based testing, snapshot tests for prompts, eval-based tests for agents\nPydantic v2 fluency, type-hinted code throughout\nNice-to-haves \nRAG production experience (vector stores: Pinecone, Qdrant, pgvector)\nProduction incident command for LLM-powered systems\nML engineering background (model serving, feature engineering)\nAnthropic / Claude API experience in addition to OpenAI\nData pipeline experience (Airflow, Dagster, Prefect)\nDomain knowledge in fitness / health / wearables\nExperience working with cross-team JSI / native bridges (the Python core integrates with a mobile JSI layer)\nTech stack\nPython\nAI\nFastAPI\nCelery\nRedis\nMongoDB\nStorage\nPostgreSQL\nAudit\nSRE\nREST API\nAPI\nDesign Patterns\nTesting\npytest\nAirflow","description_format":"text","description_chars":4515,"description_truncated":false,"requirements":{"experience_years_min":7,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Information Technology"],"lifecycle":[{"event":"open","at":"2026-10-08T22:25:03Z"}],"visa":[],"liveness":{"score":66,"band":"ok","label":"Likely open","p_open":0.85,"p_active":0.86,"p_room":0.9,"age_days":16,"expected_fill_days":38,"reasons":["seen:16","velocity","win:mid"],"computed_at":"2026-10-12T06:55:09Z"},"pay":{"stated_usd_annual":102000,"is_top_pay":false},"html_url":"https://alion.io/job/apreel-principal-python-langgraph-engineer","json_url":"https://alion.io/job/apreel-principal-python-langgraph-engineer.json","meta":{"generated_at":"2026-10-12T20:43:15Z","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":33684,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-13T00:00:00Z"}},"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":3913594},"rest":"https://alion.io/mcp/rest/get_company?id=3913594"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fapreel-principal-python-langgraph-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%2Fapreel-principal-python-langgraph-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%2Fapreel-principal-python-langgraph-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/apreel-principal-python-langgraph-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapreel-principal-python-langgraph-engineer"}]}