{"id":1137066,"url":"https://alion.io/job/cashflo-ai-engineer","title":"AI Engineer","company":{"id":8930,"name":"CashFlo","domain":"cashflo.io","url":"https://alion.io/company/cashflo","size_band":"11-50","is_staffing_agency":false,"is_intermediary":false,"ats_vendor":"Freshteam","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"hiring_geo_confidence":"structured","locations":["Mumbai, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Anthropic","optional":false},{"name":"Computer Use","optional":false},{"name":"FastAPI","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GraphRAG","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"LangChain","optional":false},{"name":"Langfuse","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Neo4j","optional":false},{"name":"OCR","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Python","optional":false},{"name":"Rest API","optional":false},{"name":"AWS","optional":true},{"name":"Docker","optional":true},{"name":"ElasticSearch","optional":true},{"name":"GCP","optional":true},{"name":"Java","optional":true},{"name":"pgvector","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Spring Boot","optional":true}],"status":"live","first_seen_at":"2026-09-23T08:40:24Z","employer_posted_date":null,"last_verified_at":"2026-09-23T08:40:24Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"The core responsibilities for the job include the following:\nAgents that run finance workflows:\nOwn end-to-end finance workflows as autonomous agents: invoice-to-pay, three-way matching and exception handling, GL close tasks, reconciliation, and vendor and compliance checks.\nDesign tool and action surfaces over ERP systems, control flow, error recovery, human-in-the-loop checkpoints, approval and segregation-of-duties guardrails, and full auditability of every action taken on financial data\nBuild against production enterprise surfaces: SAP APIs, ERP user interfaces via computer-use agents, documents, and file-based integrations using LangGraph, LangChain, or custom orchestration.\nMemory and the finance knowledge graph:\nOwn agent memory: context management (windowing, summarization, compaction), long-term memory, retrieval and forgetting policies, and cross-cycle state for long-running agents.\nModel the finance domain as a knowledge graph: vendors, invoices, POs, GRNs, GL accounts, contracts, approvals, and their provenance in a graph database (Neo4j or equivalent) alongside vector search, ensuring every output can be substantiated for finance and audit review.\nEvaluation and model strategy:\nBuild and extend our evaluation platform: golden datasets, workflow-level metrics, regression gates in CI, automated judging calibrated against human review, and drift detection on live traffic. No change is released without a measured evaluation delta.\nWork across model families (Anthropic, OpenAI, Google, and open-weight) and own routing, which model handles which step at what quality, cost, and latency point, with tiering, cascading, and provider failover.\nScale and platform:\nOwn latency, throughput, and unit economics for agents and pipelines operating at large document and transaction volumes, maintaining p50/p95/p99 latency and cost-per-workflow targets as the customer base grows.\nMaintain the API surface (FastAPI, REST) that delivers these capabilities into our products, and mentor engineers working alongside AI systems.\nRequirements:\nAgents in production: demonstrated experience delivering a multi-step agent that performs actions in a production system, with a clear understanding of its failure modes and the controls used to contain them.\nMemory: experience designing the memory and context strategy for a long-running agent, including retention, summarization, and pruning decisions.\nEvaluation: hands-on experience building an evaluation harness, including dataset construction, metric selection, and calibration of automated judging.\nMultiple models: delivered systems on at least two model providers or families, with experience migrating a live workload between them.\nScale: experience operating an LLM or ML system in production at significant request volume, with measurable before-and-after results.\nOur Stack: Python, LangGraph/LangChain, Anthropic, OpenAI, and Google model APIs; FastAPI, PostgreSQL with pgvector, Neo4j, Elasticsearch, Java/Spring Boot, React, GCP, AWS, Docker, an in-house evals platform, and in-house OCR. Familiarity is helpful but not a prerequisite.\nPreferred / General Requirements:\nFinance, accounting, audit, or ERP (SAP) domain exposure, or a strong interest in developing domain depth.\nComputer-use or browser automation agents; GraphRAG and ontology design; document AI/OCR; fine-tuning or serving open-weight models.\nLLM tracing and observability (LangSmith, Langfuse, OpenTelemetry); enterprise AI security, governance, and compliance frameworks.\nRegular use of AI coding agents in day-to-day development; a significant share of our codebase is authored this way.","description_format":"text","description_chars":3638,"description_truncated":false,"requirements":{"experience_years_min":null,"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":["Financial Services","Lending","FinTech"],"lifecycle":[{"event":"open","at":"2026-09-23T08:40:24Z"}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":132,"reasons":["seen:0","win:early"],"computed_at":"2026-09-23T13:06:27Z"},"pay":null,"html_url":"https://alion.io/job/cashflo-ai-engineer","json_url":"https://alion.io/job/cashflo-ai-engineer.json","meta":{"generated_at":"2026-09-23T13:06:27Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers"}}